Noise Stability is Low-Dimensional Anindya De, Elchanan Mossel, Joe - - PowerPoint PPT Presentation

noise stability is low dimensional
SMART_READER_LITE
LIVE PREVIEW

Noise Stability is Low-Dimensional Anindya De, Elchanan Mossel, Joe - - PowerPoint PPT Presentation

Noise Stability is Low-Dimensional Anindya De, Elchanan Mossel, Joe Neeman Gaussian noise stability Take X and Y a pair of -correlated Gaussians in R n (0 < < 1). For a partition A = ( A 1 , . . . , A k ) of R n into k parts, define


slide-1
SLIDE 1

Noise Stability is Low-Dimensional

Anindya De, Elchanan Mossel, Joe Neeman

slide-2
SLIDE 2

Gaussian noise stability

Take X and Y a pair of ρ-correlated Gaussians in Rn (0 < ρ < 1). For a partition A = (A1, . . . , Ak) of Rn into k parts, define Stabρ(A) = Pr(X and Y land in the same part)

1

slide-3
SLIDE 3

Gaussian noise stability

Noise stable Not noise stable

2

slide-4
SLIDE 4

Gaussian noise stability

Theorem (Borell ’85) For a partition of Rn into two parts of equal Gaussian measure, Stabρ(A) ≤ 1 2 + sin−1 ρ π . Equality is attained for a partition into half-spaces.

3

slide-5
SLIDE 5

Gaussian noise stability

Theorem (Borell ’85) For a partition of Rn into two parts of equal Gaussian measure, Stabρ(A) ≤ 1 2 + sin−1 ρ π . Equality is attained for a partition into half-spaces.

  • well-known links to computational complexity (KKMO ’05)

3

slide-6
SLIDE 6

Gaussian noise stability

Theorem (Borell ’85) For a partition of Rn into two parts of equal Gaussian measure, Stabρ(A) ≤ 1 2 + sin−1 ρ π . Equality is attained for a partition into half-spaces.

  • well-known links to computational complexity (KKMO ’05)
  • one-dimensional phenomenon

3

slide-7
SLIDE 7

Gaussian noise stability

Theorem (???) For a partition of Rn into three parts of equal Gaussian measure, ???

3

slide-8
SLIDE 8

Gaussian noise stability

Conjecture (Peace sign conjecture) The optimal partition looks like a peace sign.

4

slide-9
SLIDE 9

Gaussian noise stability

Conjecture (Peace sign conjecture) The optimal partition looks like a peace sign. (two-dimensional phenomenon)

4

slide-10
SLIDE 10

Gaussian noise stability

Conjecture (Peace sign conjecture) The optimal partition looks like a peace sign. (two-dimensional phenomenon) Conjecture (Multi-dimensional peace sign conjecture) For partitions into k equal measures, the optimal partition occurs in Rk−1. It looks like a multi-dimensional peace sign.

4

slide-11
SLIDE 11

Gaussian noise stability

Theorem (De-Mossel-N.) For any k and any ǫ > 0, there is a computable n0 = n0(k, ǫ) such that an ǫ-approximately optimal partition occurs in Rn0.

5

slide-12
SLIDE 12

Gaussian noise stability

Theorem (De-Mossel-N.) For any k and any ǫ > 0, there is a computable n0 = n0(k, ǫ) such that an ǫ-approximately optimal partition occurs in Rn0. Corollary The optimal value of k-part noise stability is computable.

5

slide-13
SLIDE 13

Gaussian noise stability

Theorem (De-Mossel-N.) For any k and any ǫ > 0, there is a computable n0 = n0(k, ǫ) such that an ǫ-approximately optimal partition occurs in Rn0. Corollary The optimal value of k-part noise stability is computable. Corollary (sort of) The non-interactive correlation distillation value with k-ary outputs is computable.

5

slide-14
SLIDE 14

Correlation distillation

Goal: produce uniform output, agree with maximal probability. What is the probability of agreement?

6

slide-15
SLIDE 15

Correlation distillation

Goal: produce uniform output, agree with maximal probability. What is the probability of agreement? Ghazi-Kamath-Sudan ’16: reduction to correlated Gaussian signals

6

slide-16
SLIDE 16

The main theorem

Theorem (De-Mossel-N.) For any k and any ǫ > 0, there is a computable n0 = n0(k, ǫ) such that an ǫ-approximately optimal partition occurs in Rn0.

7

slide-17
SLIDE 17

Proof outline

Idea: take an optimal partition in Rn (n huge) and try to “simulate” it in Rn0.

8

slide-18
SLIDE 18

Proof outline

Idea: take an optimal partition in Rn (n huge) and try to “simulate” it in Rn0.

  • 1. An optimal partition is close to a bounded-degree polynomial

threshold function (PTF)

8

slide-19
SLIDE 19

Proof outline

Idea: take an optimal partition in Rn (n huge) and try to “simulate” it in Rn0.

  • 1. An optimal partition is close to a bounded-degree polynomial

threshold function (PTF)

  • 2. A bounded-degree PTF can be approximately simulated by a

bounded-degree PTF on a bounded number of variables

8

slide-20
SLIDE 20

Step 1: approximation by polynomials

slide-21
SLIDE 21

Approximation by polynomials

Think of a partition as a function f : Rn → {e1, . . . , ek} ⊂ Rk.

9

slide-22
SLIDE 22

Approximation by polynomials

Think of a partition as a function f : Rn → {e1, . . . , ek} ⊂ Rk. Hermite expansion f (x) =

  • α,i

ˆ fα,iHα(x)ei

9

slide-23
SLIDE 23

Approximation by polynomials

Think of a partition as a function f : Rn → {e1, . . . , ek} ⊂ Rk. Hermite expansion f (x) =

  • α,i

ˆ fα,iHα(x)ei Facts: 1 =

  • α,i

ˆ f 2

α,i and Stabρ(f ) =

  • α,i

ρdeg(Hα) ˆ f 2

α,i 9

slide-24
SLIDE 24

Approximation by polynomials

Think of a partition as a function f : Rn → {e1, . . . , ek} ⊂ Rk. Hermite expansion f (x) =

  • α,i

ˆ fα,iHα(x)ei Facts: 1 =

  • α,i

ˆ f 2

α,i and Stabρ(f ) =

  • α,i

ρdeg(Hα) ˆ f 2

α,i

Idea: noise stability ⇒ lots of “low-degree” weight ⇒ approximate f by truncating the expansion

9

slide-25
SLIDE 25

Approximation by polynomials

Think of a partition as a function f : Rn → {e1, . . . , ek} ⊂ Rk. Hermite expansion f (x) =

  • α,i

ˆ fα,iHα(x)ei Facts: 1 =

  • α,i

ˆ f 2

α,i and Stabρ(f ) =

  • α,i

ρdeg(Hα) ˆ f 2

α,i

Idea: noise stability ⇒ lots of “low-degree” weight ⇒ approximate f by truncating the expansion Real proof goes through a smoothing/rounding procedure, and a connection with Gaussian surface area (KNOW ’15).

9

slide-26
SLIDE 26

Step 2: dimension reduction

slide-27
SLIDE 27

Polynomial structure theorem (De-Servedio)

where ℓ is bounded and v1, . . . , vℓ are “nice”

10

slide-28
SLIDE 28

Polynomial Central Limit Theorem (De-Servedio)

11

slide-29
SLIDE 29

Polynomial Central Limit Theorem (De-Servedio)

“Nice” polynomials satisfy a CLT, so they may as well be linear functions of ℓ variables

11

slide-30
SLIDE 30

Polynomial Central Limit Theorem (De-Servedio)

“Nice” polynomials satisfy a CLT, so they may as well be linear functions of ℓ variables

11

slide-31
SLIDE 31

Open problem

Conjecture (Peace sign conjecture) The optimal partition looks like a peace sign.

12

slide-32
SLIDE 32

Thank you!