- stein's method, logarithmic sobolev and transport...

73
Stein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and HongJuan Zhou University of Kansas November 2017 Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 1 / 35

Upload: others

Post on 30-May-2020

6 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Stein’s method, logarithmic Sobolev and transport inequalities

Arturo Jaramillo and HongJuan Zhou

University of Kansas

November 2017

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 1 / 35

Page 2: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Introduction

For d ≥ 1, let γ(dx) denote the standard Gaussian measure in Rd .

Theorem (Classical logarithmic Sobolev inequality for γ)For every probability measure ν of the form ν(dx) = h(x)γ(dx), withh : Rd → R+, we have that the relative entropy and Fisher information ofν with respect to γ, defined by

H(ν|γ) :=∫Rd

h(x) log(h(x))γ(dx), I(ν|γ) :=∫Rd

|∇h(x)|2h(x) γ(dx),

satisfy

H(ν|γ) ≤ 12 I(ν|γ).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 2 / 35

Page 3: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Introduction

For d ≥ 1, let γ(dx) denote the standard Gaussian measure in Rd .

Theorem (Classical logarithmic Sobolev inequality for γ)For every probability measure ν of the form ν(dx) = h(x)γ(dx), withh : Rd → R+, we have that the relative entropy and Fisher information ofν with respect to γ, defined by

H(ν|γ) :=∫Rd

h(x) log(h(x))γ(dx), I(ν|γ) :=∫Rd

|∇h(x)|2h(x) γ(dx),

satisfy

H(ν|γ) ≤ 12 I(ν|γ).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 2 / 35

Page 4: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Introduction

For d ≥ 1, let γ(dx) denote the standard Gaussian measure in Rd .

Theorem (Classical logarithmic Sobolev inequality for γ)For every probability measure ν of the form ν(dx) = h(x)γ(dx), withh : Rd → R+, we have that the relative entropy and Fisher information ofν with respect to γ, defined by

H(ν|γ) :=∫Rd

h(x) log(h(x))γ(dx), I(ν|γ) :=∫Rd

|∇h(x)|2h(x) γ(dx),

satisfy

H(ν|γ) ≤ 12 I(ν|γ).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 2 / 35

Page 5: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Introduction

Objective:Prove a sharper version of the logarithmic Sobolev inequality that includesthe so called “Stein discrepancy”, which is a type of measure of how close

is a measure to the standard d-dimensional distribution.

Note: in the sequel, we will assume that ν(dx) = h(x)γ(dx).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 3 / 35

Page 6: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Introduction

Objective:Prove a sharper version of the logarithmic Sobolev inequality that includesthe so called “Stein discrepancy”, which is a type of measure of how close

is a measure to the standard d-dimensional distribution.

Note: in the sequel, we will assume that ν(dx) = h(x)γ(dx).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 3 / 35

Page 7: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Preliminaries

A matrix-valued map τν : Rd → Rd×d is said to be a Stein kernel for ν, iffor every smooth ϕ : Rd → R,∫

Rdx · ∇ϕ(x)ν(dx) =

∫Rd〈τν(x),Hess[ϕ](x)〉HS ν(dx).

where 〈A,B〉HS := tr(A∗B) is the Hilbert-Schmidt inner product on Rd×d .

Remark- The matrix τν(x) can be taken to be symmetric.- In the case where ν = γ, we can take τν(x) := Id = identity matrix, since∫

Rdx · ∇ϕ(x)ν(dx) =

∫Rd

∆ϕ(x)ν(dx) =∫Rd〈Id ,Hess[ϕ](x)〉HS ν(dx).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 4 / 35

Page 8: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Preliminaries

A matrix-valued map τν : Rd → Rd×d is said to be a Stein kernel for ν, iffor every smooth ϕ : Rd → R,∫

Rdx · ∇ϕ(x)ν(dx) =

∫Rd〈τν(x),Hess[ϕ](x)〉HS ν(dx).

where 〈A,B〉HS := tr(A∗B) is the Hilbert-Schmidt inner product on Rd×d .

Remark- The matrix τν(x) can be taken to be symmetric.

- In the case where ν = γ, we can take τν(x) := Id = identity matrix, since∫Rd

x · ∇ϕ(x)ν(dx) =∫Rd

∆ϕ(x)ν(dx) =∫Rd〈Id ,Hess[ϕ](x)〉HS ν(dx).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 4 / 35

Page 9: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Preliminaries

A matrix-valued map τν : Rd → Rd×d is said to be a Stein kernel for ν, iffor every smooth ϕ : Rd → R,∫

Rdx · ∇ϕ(x)ν(dx) =

∫Rd〈τν(x),Hess[ϕ](x)〉HS ν(dx).

where 〈A,B〉HS := tr(A∗B) is the Hilbert-Schmidt inner product on Rd×d .

Remark- The matrix τν(x) can be taken to be symmetric.- In the case where ν = γ, we can take τν(x) := Id = identity matrix,

since∫Rd

x · ∇ϕ(x)ν(dx) =∫Rd

∆ϕ(x)ν(dx) =∫Rd〈Id ,Hess[ϕ](x)〉HS ν(dx).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 4 / 35

Page 10: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Preliminaries

A matrix-valued map τν : Rd → Rd×d is said to be a Stein kernel for ν, iffor every smooth ϕ : Rd → R,∫

Rdx · ∇ϕ(x)ν(dx) =

∫Rd〈τν(x),Hess[ϕ](x)〉HS ν(dx).

where 〈A,B〉HS := tr(A∗B) is the Hilbert-Schmidt inner product on Rd×d .

Remark- The matrix τν(x) can be taken to be symmetric.- In the case where ν = γ, we can take τν(x) := Id = identity matrix, since∫

Rdx · ∇ϕ(x)ν(dx) =

∫Rd

∆ϕ(x)ν(dx) =∫Rd〈Id ,Hess[ϕ](x)〉HS ν(dx).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 4 / 35

Page 11: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Improved log-Sobolev inequality

Whenever τν exists, we define the Stein discrepancy of ν with respect toγ, as

S(ν|γ) :=(∫

Rd‖τν(x)− Id‖2HSγ(dx)

) 12.

The main result of the talk is the following

Theorem (Improved logarithmic Sobolev inequality, HSI)

H(ν|γ) ≤ 12S(ν|γ)2 log

(1 + I(ν|γ)

S(ν|γ)2

)In the sequel, we will assume that 0 < S(ν|γ), I(ν|γ) <∞.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 5 / 35

Page 12: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Improved log-Sobolev inequality

Whenever τν exists, we define the Stein discrepancy of ν with respect toγ, as

S(ν|γ) :=(∫

Rd‖τν(x)− Id‖2HSγ(dx)

) 12.

The main result of the talk is the following

Theorem (Improved logarithmic Sobolev inequality, HSI)

H(ν|γ) ≤ 12S(ν|γ)2 log

(1 + I(ν|γ)

S(ν|γ)2

)

In the sequel, we will assume that 0 < S(ν|γ), I(ν|γ) <∞.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 5 / 35

Page 13: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Improved log-Sobolev inequality

Whenever τν exists, we define the Stein discrepancy of ν with respect toγ, as

S(ν|γ) :=(∫

Rd‖τν(x)− Id‖2HSγ(dx)

) 12.

The main result of the talk is the following

Theorem (Improved logarithmic Sobolev inequality, HSI)

H(ν|γ) ≤ 12S(ν|γ)2 log

(1 + I(ν|γ)

S(ν|γ)2

)In the sequel, we will assume that 0 < S(ν|γ), I(ν|γ) <∞.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 5 / 35

Page 14: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Basic results of the Stein kernel

Assume that τν = τ i ,jν 1≤i ,j≤d exists and is symmetric. Recall that τν

satisfies ∫Rd

x · ∇ϕ(x)ν(dx) =∫Rd〈τν(x),Hess[ϕ](x)〉HS ν(dx). (1)

Thus, for 1 ≤ i , j ≤ d fixed, we can take ϕ(x) = xi and ϕ(x) = xi xj in (1),in order to obtain∫

xν(dx) = 0, and∫

xi xjν(dx) =∫τ i ,jν (x)ν(dx).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 6 / 35

Page 15: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Basic results of the Stein kernel

Assume that τν = τ i ,jν 1≤i ,j≤d exists and is symmetric. Recall that τν

satisfies ∫Rd

x · ∇ϕ(x)ν(dx) =∫Rd〈τν(x),Hess[ϕ](x)〉HS ν(dx). (1)

Thus, for 1 ≤ i , j ≤ d fixed, we can take ϕ(x) = xi

and ϕ(x) = xi xj in (1),in order to obtain∫

xν(dx) = 0, and∫

xi xjν(dx) =∫τ i ,jν (x)ν(dx).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 6 / 35

Page 16: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Basic results of the Stein kernel

Assume that τν = τ i ,jν 1≤i ,j≤d exists and is symmetric. Recall that τν

satisfies ∫Rd

x · ∇ϕ(x)ν(dx) =∫Rd〈τν(x),Hess[ϕ](x)〉HS ν(dx). (1)

Thus, for 1 ≤ i , j ≤ d fixed, we can take ϕ(x) = xi and ϕ(x) = xi xj in (1),in order to obtain

∫xν(dx) = 0, and

∫xi xjν(dx) =

∫τ i ,jν (x)ν(dx).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 6 / 35

Page 17: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Basic results of the Stein kernel

Assume that τν = τ i ,jν 1≤i ,j≤d exists and is symmetric. Recall that τν

satisfies ∫Rd

x · ∇ϕ(x)ν(dx) =∫Rd〈τν(x),Hess[ϕ](x)〉HS ν(dx). (1)

Thus, for 1 ≤ i , j ≤ d fixed, we can take ϕ(x) = xi and ϕ(x) = xi xj in (1),in order to obtain∫

xν(dx) = 0, and∫

xi xjν(dx) =∫τ i ,jν (x)ν(dx).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 6 / 35

Page 18: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

The Ornstein-Uhlenbeck semigroup

Let Ptt≥0 denote the Ornstein-Uhlenbeck semigroup in Rd , withinfinitesimal generator

Lf = ∆f − x · ∇f , for f ∈ C2(Rd ;R).

It is well known that Pt can be written as

Pt f (x) =∫Rd

f(e−tx +

√1− e−2ty

)γ(dy).

This expression is called Mehler formula. From it, we can easily obtain

∇Pt f = e−tPt(∇f ),

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 7 / 35

Page 19: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

The Ornstein-Uhlenbeck semigroup

Let Ptt≥0 denote the Ornstein-Uhlenbeck semigroup in Rd , withinfinitesimal generator

Lf = ∆f − x · ∇f , for f ∈ C2(Rd ;R).

It is well known that Pt can be written as

Pt f (x) =∫Rd

f(e−tx +

√1− e−2ty

)γ(dy).

This expression is called Mehler formula.

From it, we can easily obtain

∇Pt f = e−tPt(∇f ),

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 7 / 35

Page 20: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

The Ornstein-Uhlenbeck semigroup

Let Ptt≥0 denote the Ornstein-Uhlenbeck semigroup in Rd , withinfinitesimal generator

Lf = ∆f − x · ∇f , for f ∈ C2(Rd ;R).

It is well known that Pt can be written as

Pt f (x) =∫Rd

f(e−tx +

√1− e−2ty

)γ(dy).

This expression is called Mehler formula. From it, we can easily obtain

∇Pt f = e−tPt(∇f ),

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 7 / 35

Page 21: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

The Ornstein-Uhlenbeck semigroup

By using Mehler’s formula, as well as an integration by parts argument, wecan show that

Pt(∇f )(x) = 1√1− e−2t

∫Rd

yf (e−tx +√

1− e−2ty)γ(dy).

The generator L satisfies the following integration by parts formula∫Rd

f (x)Lg(x)γ(dx) = −∫∇f (x) · ∇g(x)γ(dx).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 8 / 35

Page 22: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

The Ornstein-Uhlenbeck semigroup

By using Mehler’s formula, as well as an integration by parts argument, wecan show that

Pt(∇f )(x) = 1√1− e−2t

∫Rd

yf (e−tx +√

1− e−2ty)γ(dy).

The generator L satisfies the following integration by parts formula∫Rd

f (x)Lg(x)γ(dx) = −∫∇f (x) · ∇g(x)γ(dx).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 8 / 35

Page 23: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Formulas for I(ν|γ)

The Fisher information I(ν|γ) can be written in terms of L as follows

I(ν|γ) =∫Rd

|∇h(x)|2h(x) γ(dx)

=∫Rd|∇ log h(x)|2h(x)γ(dx)

= −∫Rd

(L log h(x)

)h(x)γ(dx).

Thus, by setting v := log h, we get

I(ν|γ) = −∫RdLv(x)ν(dx).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 9 / 35

Page 24: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Formulas for I(ν|γ)

The Fisher information I(ν|γ) can be written in terms of L as follows

I(ν|γ) =∫Rd

|∇h(x)|2h(x) γ(dx)

=∫Rd|∇ log h(x)|2h(x)γ(dx)

= −∫Rd

(L log h(x)

)h(x)γ(dx).

Thus, by setting v := log h, we get

I(ν|γ) = −∫RdLv(x)ν(dx).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 9 / 35

Page 25: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Organization of the proof

Define vt := log Pth and νt(dx) = Pthγ(dx).

Replacing h by Pth andusing the symmetry of Pt in the previous expressions, we get

I(νt |γ) = −∫RdLPtvt(x)ν(dx).

For proving the HSI, we use the integrated Bruijn’s formula

H(ν|γ) =∫ ∞

0I(νt |γ)dt.

The result is obtained by obtaining different type of bounds for Iγ(Pth),depending on whether t ≈ 0 or t ≈ ∞.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 10 / 35

Page 26: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Organization of the proof

Define vt := log Pth and νt(dx) = Pthγ(dx). Replacing h by Pth andusing the symmetry of Pt in the previous expressions, we get

I(νt |γ) = −∫RdLPtvt(x)ν(dx).

For proving the HSI, we use the integrated Bruijn’s formula

H(ν|γ) =∫ ∞

0I(νt |γ)dt.

The result is obtained by obtaining different type of bounds for Iγ(Pth),depending on whether t ≈ 0 or t ≈ ∞.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 10 / 35

Page 27: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Organization of the proof

Define vt := log Pth and νt(dx) = Pthγ(dx). Replacing h by Pth andusing the symmetry of Pt in the previous expressions, we get

I(νt |γ) = −∫RdLPtvt(x)ν(dx).

For proving the HSI, we use the integrated Bruijn’s formula

H(ν|γ) =∫ ∞

0I(νt |γ)dt.

The result is obtained by obtaining different type of bounds for Iγ(Pth),depending on whether t ≈ 0 or t ≈ ∞.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 10 / 35

Page 28: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Organization of the proof

Define vt := log Pth and νt(dx) = Pthγ(dx). Replacing h by Pth andusing the symmetry of Pt in the previous expressions, we get

I(νt |γ) = −∫RdLPtvt(x)ν(dx).

For proving the HSI, we use the integrated Bruijn’s formula

H(ν|γ) =∫ ∞

0I(νt |γ)dt.

The result is obtained by obtaining different type of bounds for Iγ(Pth),depending on whether t ≈ 0 or t ≈ ∞.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 10 / 35

Page 29: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Decay of I(νt |γ) and S(νt |γ)

The following results are the main ingredients for the proof of the HSI

TheoremFor every t > 0,

I(νt |γ) ≤ e−2t I(ν0|γ),

and

I(νt |γ) ≤ e−4t

1− e−2t ‖τν − Id‖22,ν = e−4t

1− e−2t S(ν0|γ)2.

Moreover, the Stein discrepancy satisfies

S(νt |γ) ≤ e−2tS(ν0|γ).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 11 / 35

Page 30: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Proof of the LSI inequality

Using the previous bounds, we have that for every u > 0,

H(ν|γ) =∫ u

0Iγ(Pth)dt +

∫ ∞u

Iγ(Pth)dt

≤ I(ν|γ)∫ u

0e−2tdt + S(ν|γ)2

∫ ∞u

e−4t

1− e−2t dt

≤ 12 I(ν|γ)(1− e−2u) + 1

2S(ν|γ)2(−e−2u − log(1− e−2u)).

Optimizing in u (computations are easier if we define 1− e−2u = r), weobtain the result.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 12 / 35

Page 31: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Bound for I(νt |γ), when t is large

We have that

Iγ(Pth) = −∫RdLPtvt(x)ν(dx) = −

∫Rd

[∆Ptvt(x)− x · vt(x)]ν(dx)

=∫Rd〈τν(x)− Id ,Hess(Ptvt)〉HS ν(dx)

To rewrite the Hessian, notice that

∂i ,jPtvt(x) = e−2tPt(∂i ,jvt)(x)

= e−2t√

1− e−2t

∫Rd

yi∂vt∂xj

(e−tx +√

1− e−2ty)γ(dx)

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 13 / 35

Page 32: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Bound for I(νt |γ), when t is largeFrom here it follows that∫

Rd〈τν(x)− Id ,Hess(Ptvt(x))〉HS ν(dx)

= e−2t√

1− e−2t

∫Rd

∫Rd

[(τν(x)−Id )y ·∇vt(e−tx+

√1− e−2ty)

]ν(dx)γ(dy)

This implies, after two suitable applications of the Cauchy-Schwarzinequality, that

Iγ(Pth) ≤ e−2t√

1− e−2t

∫Rd

∫Rd|(τν(x)− Id )y |

× |∇vt(e−tx +√

1− e−2ty)|ν(dx)γ(dy)

≤ e−2t√

1− e−2t

(∫Rd‖τν(x)− Id‖2ν(dx)

∫Rd

Pt |∇vt |2(x)ν(dx)) 1

2

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 14 / 35

Page 33: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Bound for I(νt |γ), when t is large

Thus, since∫Rd

Pt |∇vt |2(x)ν(dx) =∫Rd

Pt |∇vt(x)|2h(x)γ(dx)

=∫Rd|∇vt(x)|2Pth(x)γ(dx) = Iγ(Pth),

we get that

Iγ(Pth) ≤ e−2t√

1− e−2t

(∫Rd‖τν(x)− Id‖2ν(dx)

) 12Iγ(Pth)

12 ,

which implies the desired inequality

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 15 / 35

Page 34: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Sketch of the proof of S(νt |γ) ≤ e−2tS(ν0|γ)

The idea consists on finding a Stein kernel for νt . This is obtained usingintegration by parts, and is given by

τνt (x) := e−2t Pthτν(x)Pth + (1− e−2t)Id .

Therefore,∫Rd‖τνt − Id‖2HS ≤ e−4

∫Rd

‖Pt [h(τν − Id )](x)‖2HSPth(x) γ(dx).

By the Cauchy-Schwarz inequality,

‖Pt [h(τν − Id )](x)‖2HS ≤ Pt [h‖τν − Id‖2HS ](x)Pth(x).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 16 / 35

Page 35: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Sketch of the proof of S(νt |γ) ≤ e−2tS(ν0|γ)

The idea consists on finding a Stein kernel for νt . This is obtained usingintegration by parts, and is given by

τνt (x) := e−2t Pthτν(x)Pth + (1− e−2t)Id .

Therefore,∫Rd‖τνt − Id‖2HS ≤ e−4

∫Rd

‖Pt [h(τν − Id )](x)‖2HSPth(x) γ(dx).

By the Cauchy-Schwarz inequality,

‖Pt [h(τν − Id )](x)‖2HS ≤ Pt [h‖τν − Id‖2HS ](x)Pth(x).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 16 / 35

Page 36: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Sketch of the proof of S(νt |γ) ≤ e−2tS(ν0|γ)

The idea consists on finding a Stein kernel for νt . This is obtained usingintegration by parts, and is given by

τνt (x) := e−2t Pthτν(x)Pth + (1− e−2t)Id .

Therefore,∫Rd‖τνt − Id‖2HS ≤ e−4

∫Rd

‖Pt [h(τν − Id )](x)‖2HSPth(x) γ(dx).

By the Cauchy-Schwarz inequality,

‖Pt [h(τν − Id )](x)‖2HS ≤ Pt [h‖τν − Id‖2HS ](x)Pth(x).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 16 / 35

Page 37: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Consequently,∫Rd‖τνt (x)− Id‖2HSν

t(dx) ≤ e−4t∫Rd

Pt [h‖τν − Id‖HS ](x)γ(dx)

≤ e−4t∫Rd

h(x)‖τν(x)− Id‖2HSγ(dx)

= e−4t∫Rd‖τν − Id‖2HSν(dx),

which gives the desired inequality.

Remark: The Stein’s kernel τνt admits the probabilistic representation

τνt (x) = E[e−2tτν(F ) + (1− e−2t)Id | Ft = x ], νt(dx) -a.e.

where on some probability space (Ω,F ,P), F has distribution ν,Ft := e−tF +

√1− e−2tZ , where Z is a d-dimensional Gaussian vector,

independent of F .

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 17 / 35

Page 38: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Consequently,∫Rd‖τνt (x)− Id‖2HSν

t(dx) ≤ e−4t∫Rd

Pt [h‖τν − Id‖HS ](x)γ(dx)

≤ e−4t∫Rd

h(x)‖τν(x)− Id‖2HSγ(dx)

= e−4t∫Rd‖τν − Id‖2HSν(dx),

which gives the desired inequality.Remark: The Stein’s kernel τνt admits the probabilistic representation

τνt (x) = E[e−2tτν(F ) + (1− e−2t)Id | Ft = x ], νt(dx) -a.e.

where on some probability space (Ω,F ,P), F has distribution ν,Ft := e−tF +

√1− e−2tZ , where Z is a d-dimensional Gaussian vector,

independent of F .

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 17 / 35

Page 39: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Introduction

Objective:

Give an improved form of exponential decay of entropy.Apply Stein’s discrepancy in deriving concentration inequalities.Explore the relationship between transport distances and Stein’sdiscrepancy. The WSH inequality, as an improvement of theTalagrand quadratic transportation cost inequality, provides a sharperbound on the Wasserstein distance W2, which involves Stein’sdiscrepancy and relative entropy. Finally we bound Wp distance byStein’s discrepancy.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 18 / 35

Page 40: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Exponential decay of entropy from HSI

The classical logarithmic Sobolev inequality ensures the exponential decayof the relative entropy

H(νt |γ) ≤ e−2tH(ν|γ) ,

along the O-U semigroup, i.e., dνt = Pthdγ.

Now, applying HSI produces a reinforcement of this exponential decayunder the finiteness of the Stein discrepancy.

CorollaryLet ν with Stein discrepancy S(ν|γ) = S. For any t ≥ 0,

H(νt |γ) ≤ e−4t

e−2t + 1−e−2t

S2 H(ν|γ)H(ν|γ) ≤ e−4t

1− e−2t S2(ν|γ) .

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 19 / 35

Page 41: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Exponential decay of entropy from HSI

The classical logarithmic Sobolev inequality ensures the exponential decayof the relative entropy

H(νt |γ) ≤ e−2tH(ν|γ) ,

along the O-U semigroup, i.e., dνt = Pthdγ.Now, applying HSI produces a reinforcement of this exponential decayunder the finiteness of the Stein discrepancy.

CorollaryLet ν with Stein discrepancy S(ν|γ) = S. For any t ≥ 0,

H(νt |γ) ≤ e−4t

e−2t + 1−e−2t

S2 H(ν|γ)H(ν|γ) ≤ e−4t

1− e−2t S2(ν|γ) .

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 19 / 35

Page 42: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Sketch of proof: Applying HSI inequality to νt implies that

H(νt |γ) ≤ e−4tS2

2 log(1 + e4t I(νt |γ)S2 ).

Set U(t) = e4t

S2 H(νt |γ), then

e2U − 1− 4U ≤ −U ′ .

−2U + 2U2 ≤ −U ′ .

Setting V (t) = e−2tU(t), we get 2e2tV 2(t) ≤ −V ′(t), such that afterintegration,

e2t − 1 ≤ 1V (t) −

1V (0) .

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 20 / 35

Page 43: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Stein discrepancy and concentration inequalities

For the standard Gaussian measure γ, for any 1-Lipschitz functionu : Rd → R with mean zero,

γ(u ≥ r) ≤ e−r2/2 ,

or equivalently, ‖u‖p,γ := (∫Rd |u|pdγ)1/p ≤ C√p, p ≥ 1. Now let ν have

Stein kernel τν , do we have a similar result for ‖u‖p,ν?

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 21 / 35

Page 44: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Theorem (Moment bounds and Stein discrepancy)

Let ν have Stein kernel τν . There exists a positive constant C such that forany 1-Lipschitz function u : Rd → R with

∫Rd udν = 0, and every p ≥ 2,

(∫Rd|u|pdν

)1/p≤ C

(Sp(ν|γ) +√p

(∫Rd‖τν‖p/2

op dν)1/p

)

Here, the p-Stein discrepancy is given by

Sp(ν|γ) =(∫

Rd‖τν − Id‖pHSdν

)1/p.

Taking into account of ‖τν‖op ≤ 1 + ‖τν − Id‖HS, we have

‖u‖p,ν ≤ C(

Sp(ν|γ) +√p +√p√

Sp(ν|γ))

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 22 / 35

Page 45: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Theorem (Moment bounds and Stein discrepancy)

Let ν have Stein kernel τν . There exists a positive constant C such that forany 1-Lipschitz function u : Rd → R with

∫Rd udν = 0, and every p ≥ 2,

(∫Rd|u|pdν

)1/p≤ C

(Sp(ν|γ) +√p

(∫Rd‖τν‖p/2

op dν)1/p

)

Here, the p-Stein discrepancy is given by

Sp(ν|γ) =(∫

Rd‖τν − Id‖pHSdν

)1/p.

Taking into account of ‖τν‖op ≤ 1 + ‖τν − Id‖HS, we have

‖u‖p,ν ≤ C(

Sp(ν|γ) +√p +√p√

Sp(ν|γ))

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 22 / 35

Page 46: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

An example of illustration of the theorem

Consider X a centered random variable on a probabilit space with values inRd . Let X1, . . . ,Xn be independent copies of X . Assume X has the law νadmitting a Stein kernel τν . Set Tn = 1√

n∑n

k=1 Xk . A Stein kernel τνn ofthe law νn of Tn is

τνn = E(

1n

n∑k=1

τν(Xk)|Tn

).

Hence,

Sp(νn|γ) ≤ E(‖1

n

n∑k=1

(τν(Xk)− Id)‖pHS

)1/p

≤ Kpn−1/2Sp(ν|γ)

which follows from Rosenthal’s inequality. Kp = O(p).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 23 / 35

Page 47: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

An example of illustration of the theorem

Consider X a centered random variable on a probabilit space with values inRd . Let X1, . . . ,Xn be independent copies of X . Assume X has the law νadmitting a Stein kernel τν . Set Tn = 1√

n∑n

k=1 Xk . A Stein kernel τνn ofthe law νn of Tn is

τνn = E(

1n

n∑k=1

τν(Xk)|Tn

).

Hence,

Sp(νn|γ) ≤ E(‖1

n

n∑k=1

(τν(Xk)− Id)‖pHS

)1/p

≤ Kpn−1/2Sp(ν|γ)

which follows from Rosenthal’s inequality. Kp = O(p).Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 23 / 35

Page 48: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

For any 1-Lipschitz function u : Rd → R such that E(u(Tn)) = 0, byTheorem 5,

‖u(Tn)‖Lp ≤ C√p(1 + n−1/2√pSp + n−1/4√

pSp) .

By Markov’s inequality, one can deduce a concentration inequality for Tn.For example, if Sp = O(pα) for some α > 0, then ‖u(Tn)‖Lp ≤ C√p forany p ≤ n

12α+2 . Then

P(|u(Tn)| ≥ r) ≤(C√p

r

)p,

with p ∼ r2

4C2 . Optimizing p gives

P(u(Tn) ≥ r) ≤ C ′e−r2/C ′ ,

for all 0 ≤ r ≤ rn where rn ∼ n1

4α+4 .

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 24 / 35

Page 49: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

For any 1-Lipschitz function u : Rd → R such that E(u(Tn)) = 0, byTheorem 5,

‖u(Tn)‖Lp ≤ C√p(1 + n−1/2√pSp + n−1/4√

pSp) .

By Markov’s inequality, one can deduce a concentration inequality for Tn.For example, if Sp = O(pα) for some α > 0, then ‖u(Tn)‖Lp ≤ C√p forany p ≤ n

12α+2 . Then

P(|u(Tn)| ≥ r) ≤(C√p

r

)p,

with p ∼ r2

4C2 .

Optimizing p gives

P(u(Tn) ≥ r) ≤ C ′e−r2/C ′ ,

for all 0 ≤ r ≤ rn where rn ∼ n1

4α+4 .

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 24 / 35

Page 50: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

For any 1-Lipschitz function u : Rd → R such that E(u(Tn)) = 0, byTheorem 5,

‖u(Tn)‖Lp ≤ C√p(1 + n−1/2√pSp + n−1/4√

pSp) .

By Markov’s inequality, one can deduce a concentration inequality for Tn.For example, if Sp = O(pα) for some α > 0, then ‖u(Tn)‖Lp ≤ C√p forany p ≤ n

12α+2 . Then

P(|u(Tn)| ≥ r) ≤(C√p

r

)p,

with p ∼ r2

4C2 . Optimizing p gives

P(u(Tn) ≥ r) ≤ C ′e−r2/C ′ ,

for all 0 ≤ r ≤ rn where rn ∼ n1

4α+4 .

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 24 / 35

Page 51: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Recall the theorem’s conclusion(∫Rd|u|pdν

)1/p≤ C

(Sp(ν|γ) +√p

(∫Rd‖τν‖p/2

op dν)1/p

).

Sketch of the proof: Set φ(t) =∫Rd (Ptu)2qdν. Differentiating along the

semigroup and using the definition of stein kernel τν yields

φ′(t) = 2q∫

(Ptu)2q−1〈Id− τν ,Hess(Ptu)〉HS

−2q(2q − 1)∫

(Ptu)2q−2〈τν ,∇Ptu ⊗∇Ptu〉HSdν

Using |∇u| ≤ 1 and |∇Ptu| ≤ e−t , we bound

−φ′(t) ≤ c1(t, q)∫|Ptu|2q−1‖τν−Id‖Hsdν+c2(t, q)

∫|Ptu|2q−1‖τν‖opdν

From young inequality, one can deduce

−φ′(t) ≤ C(t)φ(t) + D(t).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 25 / 35

Page 52: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Recall the theorem’s conclusion(∫Rd|u|pdν

)1/p≤ C

(Sp(ν|γ) +√p

(∫Rd‖τν‖p/2

op dν)1/p

).

Sketch of the proof: Set φ(t) =∫Rd (Ptu)2qdν. Differentiating along the

semigroup and using the definition of stein kernel τν yields

φ′(t) = 2q∫

(Ptu)2q−1〈Id− τν ,Hess(Ptu)〉HS

−2q(2q − 1)∫

(Ptu)2q−2〈τν ,∇Ptu ⊗∇Ptu〉HSdν

Using |∇u| ≤ 1 and |∇Ptu| ≤ e−t , we bound

−φ′(t) ≤ c1(t, q)∫|Ptu|2q−1‖τν−Id‖Hsdν+c2(t, q)

∫|Ptu|2q−1‖τν‖opdν

From young inequality, one can deduce

−φ′(t) ≤ C(t)φ(t) + D(t).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 25 / 35

Page 53: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Recall the theorem’s conclusion(∫Rd|u|pdν

)1/p≤ C

(Sp(ν|γ) +√p

(∫Rd‖τν‖p/2

op dν)1/p

).

Sketch of the proof: Set φ(t) =∫Rd (Ptu)2qdν. Differentiating along the

semigroup and using the definition of stein kernel τν yields

φ′(t) = 2q∫

(Ptu)2q−1〈Id− τν ,Hess(Ptu)〉HS

−2q(2q − 1)∫

(Ptu)2q−2〈τν ,∇Ptu ⊗∇Ptu〉HSdν

Using |∇u| ≤ 1 and |∇Ptu| ≤ e−t , we bound

−φ′(t) ≤ c1(t, q)∫|Ptu|2q−1‖τν−Id‖Hsdν+c2(t, q)

∫|Ptu|2q−1‖τν‖opdν

From young inequality, one can deduce

−φ′(t) ≤ C(t)φ(t) + D(t).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 25 / 35

Page 54: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Wasserstein distance and Stein discrepancy

Theorem (Wasserstein distance and Stein discrepancy)For every centered probability measure ν on Rd ,

W2(ν, γ) ≤ S(ν|γ)

Remark: The measure ν is not assumed to admit a density w.r.t Lebesguemeasure on Rd .

Sketch of proof:Step 1: Assume dν = hdγ, and let vt = log Pth and dνt = Pthdγ. Thenfrom a result of Otto and Villani (2000),

d+

dt W2(ν, νt) ≤(∫

Rd|∇vt |2dνt

)1/2.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 26 / 35

Page 55: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Wasserstein distance and Stein discrepancy

Theorem (Wasserstein distance and Stein discrepancy)For every centered probability measure ν on Rd ,

W2(ν, γ) ≤ S(ν|γ)

Remark: The measure ν is not assumed to admit a density w.r.t Lebesguemeasure on Rd .Sketch of proof:Step 1: Assume dν = hdγ, and let vt = log Pth and dνt = Pthdγ. Thenfrom a result of Otto and Villani (2000),

d+

dt W2(ν, νt) ≤(∫

Rd|∇vt |2dνt

)1/2.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 26 / 35

Page 56: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Then

W2(ν, γ) ≤∫ ∞

0

(∫Rd|∇vt |2dνt

)1/2dt ≤ S(ν|γ)

∫ ∞0

e−2t√

1− e−2tdt.

Step 2: For the general case, we do a regularization procedure. Namely, fixε > 0 and introduce Fε = e−εF +

√1− e−2εZ where F and Z are

independent with laws ν and γ.The distribution of Fε, νε admits smooth density hε w.r.t γ.νε has a stein kernel τνε(x) = E(e−2ετν(F ) + (1− e−2ε)Id|Fε = x).S(νε|γ) ≤ e−2εS(ν|γ).As ε→ 0, Fε → F in L2, so W2(νε, γ)→W2(ν, γ).

W2(ν, γ) = limε→0

W2(νε, γ) ≤ lim supε→0

S(νε|γ) ≤ S(ν|γ).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 27 / 35

Page 57: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Then

W2(ν, γ) ≤∫ ∞

0

(∫Rd|∇vt |2dνt

)1/2dt ≤ S(ν|γ)

∫ ∞0

e−2t√

1− e−2tdt.

Step 2: For the general case, we do a regularization procedure. Namely, fixε > 0 and introduce Fε = e−εF +

√1− e−2εZ where F and Z are

independent with laws ν and γ.

The distribution of Fε, νε admits smooth density hε w.r.t γ.νε has a stein kernel τνε(x) = E(e−2ετν(F ) + (1− e−2ε)Id|Fε = x).S(νε|γ) ≤ e−2εS(ν|γ).As ε→ 0, Fε → F in L2, so W2(νε, γ)→W2(ν, γ).

W2(ν, γ) = limε→0

W2(νε, γ) ≤ lim supε→0

S(νε|γ) ≤ S(ν|γ).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 27 / 35

Page 58: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Then

W2(ν, γ) ≤∫ ∞

0

(∫Rd|∇vt |2dνt

)1/2dt ≤ S(ν|γ)

∫ ∞0

e−2t√

1− e−2tdt.

Step 2: For the general case, we do a regularization procedure. Namely, fixε > 0 and introduce Fε = e−εF +

√1− e−2εZ where F and Z are

independent with laws ν and γ.The distribution of Fε, νε admits smooth density hε w.r.t γ.νε has a stein kernel τνε(x) = E(e−2ετν(F ) + (1− e−2ε)Id|Fε = x).S(νε|γ) ≤ e−2εS(ν|γ).As ε→ 0, Fε → F in L2, so W2(νε, γ)→W2(ν, γ).

W2(ν, γ) = limε→0

W2(νε, γ) ≤ lim supε→0

S(νε|γ) ≤ S(ν|γ).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 27 / 35

Page 59: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Talagrand inequality and WSH inequality

The Talagrand quadratic transportation cost inequality bounds theWasserstein distance using relative entropy.

W 22 (ν, γ) ≤ 2H(ν|γ) .

Applying HSI inequality produces

Theorem (Gaussian WSH inequality)Let dν = hdγ be a centered probability measure on Rd with smoothdensity h w.r.t γ. Assume that S(ν|γ) and H(ν|γ) are positive and finite.Then

W2(ν, γ) ≤ S(ν|γ) arccos(e−H(ν|γ)S2(ν|γ) ).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 28 / 35

Page 60: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Talagrand inequality and WSH inequality

The Talagrand quadratic transportation cost inequality bounds theWasserstein distance using relative entropy.

W 22 (ν, γ) ≤ 2H(ν|γ) .

Applying HSI inequality produces

Theorem (Gaussian WSH inequality)Let dν = hdγ be a centered probability measure on Rd with smoothdensity h w.r.t γ. Assume that S(ν|γ) and H(ν|γ) are positive and finite.Then

W2(ν, γ) ≤ S(ν|γ) arccos(e−H(ν|γ)S2(ν|γ) ).

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 28 / 35

Page 61: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Sketch of proof: By HSI inequality and decay feature of Stein’sdiscrepancy,

H(νt |γ) ≤ 12S2(ν|γ) log

(1 + I(νt |γ)

S2(ν|γ)

).

Exponentiating both sides,√I(νt |γ) ≤ I(νt |γ)

S(ν|γ)√

e2H(νt |γ)S2(ν|γ) − 1

.

By the result of Otto and Villani(2000), that is, the derivative ofWasserstein distance is bounded by square root of Fisher information,

d+

dt W2(ν, νt) ≤ −ddt H(νt |γ)

S(ν|γ)√

e2H(νt |γ)S2(ν|γ) − 1

= − ddt

(S(ν|γ) arccos

(e−H(νt |γ)S2(ν|γ)

)).

Integrating between t = 0 and t =∞ yields the result.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 29 / 35

Page 62: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Sketch of proof: By HSI inequality and decay feature of Stein’sdiscrepancy,

H(νt |γ) ≤ 12S2(ν|γ) log

(1 + I(νt |γ)

S2(ν|γ)

).

Exponentiating both sides,√I(νt |γ) ≤ I(νt |γ)

S(ν|γ)√

e2H(νt |γ)S2(ν|γ) − 1

.

By the result of Otto and Villani(2000), that is, the derivative ofWasserstein distance is bounded by square root of Fisher information,

d+

dt W2(ν, νt) ≤ −ddt H(νt |γ)

S(ν|γ)√

e2H(νt |γ)S2(ν|γ) − 1

= − ddt

(S(ν|γ) arccos

(e−H(νt |γ)S2(ν|γ)

)).

Integrating between t = 0 and t =∞ yields the result.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 29 / 35

Page 63: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Sketch of proof: By HSI inequality and decay feature of Stein’sdiscrepancy,

H(νt |γ) ≤ 12S2(ν|γ) log

(1 + I(νt |γ)

S2(ν|γ)

).

Exponentiating both sides,√I(νt |γ) ≤ I(νt |γ)

S(ν|γ)√

e2H(νt |γ)S2(ν|γ) − 1

.

By the result of Otto and Villani(2000), that is, the derivative ofWasserstein distance is bounded by square root of Fisher information,

d+

dt W2(ν, νt) ≤ −ddt H(νt |γ)

S(ν|γ)√

e2H(νt |γ)S2(ν|γ) − 1

= − ddt

(S(ν|γ) arccos

(e−H(νt |γ)S2(ν|γ)

)).

Integrating between t = 0 and t =∞ yields the result.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 29 / 35

Page 64: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

HWI Inequality and the comparison with HSI inequality

Otto and Villani (2000) give the HWI inequality, which states, for alldν = hdγ,

H(ν|γ) ≤W2(ν, γ)√

I(ν|γ)− 12W 2

2 (ν, γ).

Q: can we produce an inequality involving H,W2, I,S?

Here is a possibleway for the computation

Entγ(h) =∫ t

0Iγ(Psh)ds + Entγ(Pth)

≤ Iγ(h)∫ u

0e−2sds + S2(ν|γ)

∫ t

u

e−4s

1− e−2s ds

+ e−2t

2(1− e−2t)W 22 (ν, γ) ,

following from the proof idea of HSI inequality and the reverse Talagrandinequality along the semigroup.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 30 / 35

Page 65: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

HWI Inequality and the comparison with HSI inequality

Otto and Villani (2000) give the HWI inequality, which states, for alldν = hdγ,

H(ν|γ) ≤W2(ν, γ)√

I(ν|γ)− 12W 2

2 (ν, γ).

Q: can we produce an inequality involving H,W2, I,S? Here is a possibleway for the computation

Entγ(h) =∫ t

0Iγ(Psh)ds + Entγ(Pth)

≤ Iγ(h)∫ u

0e−2sds + S2(ν|γ)

∫ t

u

e−4s

1− e−2s ds

+ e−2t

2(1− e−2t)W 22 (ν, γ) ,

following from the proof idea of HSI inequality and the reverse Talagrandinequality along the semigroup.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 30 / 35

Page 66: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Integrating out the integrals and setting α = 1− e−2u ≤ 1− e−2t = β,

H(ν|γ) ≤ 12 inf

0<α≤β≤1Φ(α, β) ,

where

Φ(α, β) = αI(ν|γ)+(α−logα)S2(ν|γ)+1− ββ

W 22 (ν, γ)+(log β−β)S2(ν|γ) .

When α = β, HWI is obtained. When β = 1, HSI is obtained.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 31 / 35

Page 67: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

HWI Vs. HSI

Consider the probability measure dνn(x) = ρn(x)dx , where

ρn(x) = 1√2π

((1− an)e−x2/2 + nane−n2x2/2

),

an ∈ [0, 1] and an = o( 1log n ).

A direct computation shows thatH(νn|γ)→ 0. Moreover,

I(νn|γ) =∫Rρ′n(x)2

ρn(x) dx − 1 ∼ n2an.

S2(νn|γ) =∫R(τn(x)− 1)2ρn(x)dx ≤ an → 0.

W2(νn, γ) ≤ √an. Also, W2(νn, γ) ≤ can for some constant c > 0.

The bound of HWI, W2(νn, γ)√

I(νn|γ)− 12W 2

2 (νn, γ) ∼ na3/2n →∞.

The bound of HSI, S2(νn|γ) log(1 + I(νn|γ)S2(νn|γ)) ∼ 2an log n→ 0.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 32 / 35

Page 68: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

HWI Vs. HSI

Consider the probability measure dνn(x) = ρn(x)dx , where

ρn(x) = 1√2π

((1− an)e−x2/2 + nane−n2x2/2

),

an ∈ [0, 1] and an = o( 1log n ). A direct computation shows that

H(νn|γ)→ 0.

Moreover,I(νn|γ) =

∫Rρ′n(x)2

ρn(x) dx − 1 ∼ n2an.

S2(νn|γ) =∫R(τn(x)− 1)2ρn(x)dx ≤ an → 0.

W2(νn, γ) ≤ √an. Also, W2(νn, γ) ≤ can for some constant c > 0.

The bound of HWI, W2(νn, γ)√

I(νn|γ)− 12W 2

2 (νn, γ) ∼ na3/2n →∞.

The bound of HSI, S2(νn|γ) log(1 + I(νn|γ)S2(νn|γ)) ∼ 2an log n→ 0.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 32 / 35

Page 69: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

HWI Vs. HSI

Consider the probability measure dνn(x) = ρn(x)dx , where

ρn(x) = 1√2π

((1− an)e−x2/2 + nane−n2x2/2

),

an ∈ [0, 1] and an = o( 1log n ). A direct computation shows that

H(νn|γ)→ 0. Moreover,I(νn|γ) =

∫Rρ′n(x)2

ρn(x) dx − 1 ∼ n2an.

S2(νn|γ) =∫R(τn(x)− 1)2ρn(x)dx ≤ an → 0.

W2(νn, γ) ≤ √an. Also, W2(νn, γ) ≤ can for some constant c > 0.

The bound of HWI, W2(νn, γ)√

I(νn|γ)− 12W 2

2 (νn, γ) ∼ na3/2n →∞.

The bound of HSI, S2(νn|γ) log(1 + I(νn|γ)S2(νn|γ)) ∼ 2an log n→ 0.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 32 / 35

Page 70: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Wp distance and Stein discrepancy

Proposition (Wp distance and Stein discrepancy)

Let ν be a centered probability measure on Rd with Stein kernel τν in thesense

∫Rd xφdν =

∫Rd τν∇φdν for every smooth test funciton φ. For every

p ≥ 1, set

‖τν − Id‖p,ν =

d∑i ,j=1

∫Rd|τ ijν − δij |pdν

1/p

.

(1) Let p ∈ [1, 2). Then

Wp(ν, γ) ≤ Cpd1−1/p‖τν − Id‖p,ν .

(2) Let p ∈ [2,∞). Then if ν has finite moments of order p, then

Wp(ν, γ) ≤ Cpd1−2/p‖τν − Id‖p,ν .

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 33 / 35

Page 71: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Idea of the proof: As usual, write vt = log Pth and dνt = Pthdγ. Aversion of ∇vt , t > 0 is given by

∇vt(x) = e−2t√

1− e−2tE ((τν(F )− Id)Z |Ft = x)

= e−2t√

1− e−2tE

d∑j=1

(τ ijν (F )− δij)Zj |Ft

.where F and Z are indepdent with laws ν and γ respectively, andFt = e−tF +

√1− e−2tZ .

Moreover,

Wp(ν, γ) ≤∫ ∞

0(∫Rd|∇vt |pdνt)1/pdt.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 34 / 35

Page 72: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Idea of the proof: As usual, write vt = log Pth and dνt = Pthdγ. Aversion of ∇vt , t > 0 is given by

∇vt(x) = e−2t√

1− e−2tE ((τν(F )− Id)Z |Ft = x)

= e−2t√

1− e−2tE

d∑j=1

(τ ijν (F )− δij)Zj |Ft

.where F and Z are indepdent with laws ν and γ respectively, andFt = e−tF +

√1− e−2tZ . Moreover,

Wp(ν, γ) ≤∫ ∞

0(∫Rd|∇vt |pdνt)1/pdt.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 34 / 35

Page 73: - Stein's method, logarithmic Sobolev and transport …math.uni.lu/.../Transport_Inequalities.pdfStein’s method, logarithmic Sobolev and transport inequalities Arturo Jaramillo and

Bibliography

Ledoux, Michel and Nourdin, Ivan and Peccati, Giovanni (2015).Stein’s method, logarithmic Sobolev and transport inequalities.Geometric and Functional Analysis. 1 256–306.

Arturo Jaramillo and HongJuan Zhou (University of Kansas) November 2017 35 / 35