Proof of the Contiguity Conjecture and Lognormal Limit for the Symmetric Perceptron

02/25/2021
by   Emmanuel Abbe, et al.
0

We consider the symmetric binary perceptron model, a simple model of neural networks that has gathered significant attention in the statistical physics, information theory and probability theory communities, with recent connections made to the performance of learning algorithms in Baldassi et al. '15. We establish that the partition function of this model, normalized by its expected value, converges to a lognormal distribution. As a consequence, this allows us to establish several conjectures for this model: (i) it proves the contiguity conjecture of Aubin et al. '19 between the planted and unplanted models in the satisfiable regime; (ii) it establishes the sharp threshold conjecture; (iii) it proves the frozen 1-RSB conjecture in the symmetric case, conjectured first by Krauth-Mézard '89 in the asymmetric case. In a recent concurrent work of Perkins-Xu [PX21], the last two conjectures were also established by proving that the partition function concentrates on an exponential scale. This left open the contiguity conjecture and the lognormal limit characterization, which are established here. In particular, our proof technique relies on a dense counter-part of the small graph conditioning method, which was developed for sparse models in the celebrated work of Robinson and Wormald.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/05/2019

Settling the relationship between Wilber's bounds for dynamic optimality

In FOCS 1986, Wilber proposed two combinatorial lower bounds on the oper...
research
04/23/2018

Small-Set Expansion in Shortcode Graph and the 2-to-2 Conjecture

Dinur, Khot, Kindler, Minzer and Safra (2016) recently showed that the (...
research
03/17/2021

The Ising antiferromagnet in the replica symmetric phase

Partition functions are an important research object in combinatorics an...
research
03/21/2018

Information Theoretic Interpretation of Deep learning

We interpret part of the experimental results of Shwartz-Ziv and Tishby ...
research
01/21/2020

On mu-Symmetric Polynomials

In this paper, we study functions of the roots of a univariate polynomia...
research
04/08/2022

Solving X^2^3n+2^2n+2^n-1+(X+1)^2^3n+2^2n+2^n-1=b in GF2^4n

This article determines all the solutions in the finite field GF2^4n of ...
research
02/20/2018

Detection limits in the high-dimensional spiked rectangular model

We study the problem of detecting the presence of a single unknown spike...

Please sign up or login with your details

Forgot password? Click here to reset