Probability Seminar: Strong freezing of the binary perceptron model

Seminar | November 30 | 3:10-4 p.m. | 340 Evans Hall

Speaker/Performer:  Shuangping Li, Stanford University

Sponsor:  Department of Statistics

We consider the binary perceptron model, a simple model of neural networks that has gathered significant attention in the statistical physics, information theory and probability theory communities. We show that at low constraint density (m=n^{1-epsilon}), the model exhibits a strong freezing phenomenon with high probability, i.e. most solutions are isolated. We prove it by a refined analysis of the log partition function. Our proof technique relies on a second moment method and cluster expansions. This is based on joint work with Allan Sly.

Event Contact:  alanmhammond@yahoo.co.uk, 510-0000000

Access Coordinator:  Alan Hammond,  alanmhammond@yahoo.co.uk,  510-000-0000