Stronger generalization bounds for deep nets via a compression approach

02/14/2018
by   Sanjeev Arora, et al.
0

Deep nets generalize well despite having more parameters than the number of training samples. Recent works try to give an explanation using PAC-Bayes and Margin-based analyses, but do not as yet result in sample complexity bounds better than naive parameter counting. The current paper shows generalization bounds that're orders of magnitude better in practice. These rely upon new succinct reparametrizations of the trained net --- a compression that is explicit and efficient. These yield generalization bounds via a simple compression-based framework introduced here. Our results also provide some theoretical justification for widespread empirical success in compressing deep nets. Analysis of correctness of our compression relies upon some newly identified “ noise stability” properties of trained deep nets, which are also experimentally verified. The study of these properties and resulting generalization bounds are also extended to convolutional nets, which had eluded earlier attempts on proving generalization.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/15/2021

Compression Implies Generalization

Explaining the surprising generalization performance of deep neural netw...
01/24/2019

Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks

Recent works have cast some light on the mystery of why deep nets fit an...
02/23/2020

De-randomized PAC-Bayes Margin Bounds: Applications to Non-convex and Non-smooth Predictors

In spite of several notable efforts, explaining the generalization of de...
06/14/2019

Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets

Mode connectivity is a surprising phenomenon in the loss landscape of de...
02/23/2020

On the generalization of bayesian deep nets for multi-class classification

Generalization bounds which assess the difference between the true risk ...
01/09/2019

Generalized Deduplication: Bounds, Convergence, and Asymptotic Properties

We study a generalization of deduplication, which enables lossless dedup...
12/05/2018

An Empirical Study towards Understanding How Deep Convolutional Nets Recognize Falls

Detecting unintended falls is essential for ambient intelligence and hea...