2021
DOI: 10.48550/arxiv.2102.13069
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

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

Abstract: 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… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

1
17
0

Year Published

2021
2021
2022
2022

Publication Types

Select...
5

Relationship

0
5

Authors

Journals

citations
Cited by 8 publications
(18 citation statements)
references
References 20 publications
1
17
0
Order By: Relevance
“…This was confirmed rigorously as an upper bound in [DS19]. For the symmetric case a similar sharp threshold α SAT (κ) is known rigorously as a κ dependent constant α(κ), as established in [PX21] and [ALS21].…”
Section: Ogp the Clustering Property And The Curious Case Of The Perc...supporting
confidence: 66%
See 1 more Smart Citation
“…This was confirmed rigorously as an upper bound in [DS19]. For the symmetric case a similar sharp threshold α SAT (κ) is known rigorously as a κ dependent constant α(κ), as established in [PX21] and [ALS21].…”
Section: Ogp the Clustering Property And The Curious Case Of The Perc...supporting
confidence: 66%
“…While the algorithm has not been adopted to the symmetric case, it is quite likely that a version of it should work here as well for some positive sufficiently small κ-dependent constant α. Heuristically, the message passing algorithm was found to be effective at small positive densities, as reported in [BZ06]. Curiously, though, it is known that the symmetric model exhibits the weak clustering property at all positive densities α > 0, as was rigorously verified recently in [PX21] and [ALS21]. Furthermore, quite remarkably, each cluster consist of singletons!…”
Section: Ogp the Clustering Property And The Curious Case Of The Perc...mentioning
confidence: 66%
“…In the whole SAT phase, zero-margin solutions are isolated, meaning that one has to flip an extensive number of weights in order to find the closest solution. This scenario was also recently confirmed in simple one-hidden layer neural networks with generic activation functions [15] and also rigorously for the symmetric perceptron [23,24]. This kind of landscape with point-like solutions suggests that finding such solution should be a hard optimization problem; however, this is contrary to the numerical evidence given by simple algorithms such as the ones based on message passing [25,26].…”
mentioning
confidence: 71%
“…e second moment analysis was done for the cases p q " 1t| | ď u and p q " 1t| | ě u in [APZ19]. For the model p q " 1t| | ď u, much ner structural results (on the typical geometry of the solution space) were obtained by [PX21,ALS21].…”
Section: Rigorous Results On the Spherical Perceptronmentioning
confidence: 99%