paper-with-me

Papers

Stronger generalization bounds for deep nets via a compression approach

2018-02-14 · ICML 2018 7 · Sanjeev Arora, Rong Ge, Behnam Neyshabur, Yi Zhang

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 \textquotedblleft noise stability\textquotedblright 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.

📄 PDF Abstract BibTeX arXiv:1802.05296

Code (0)

등록된 구현이 없습니다.

Tasks

Generalization Bounds

Similar Papers 제목 키워드 기반

Compression Implies Generalization

2021-06-15 · Allan Grønlund, Mikael Høgsgaard, Lior Kamma, Kasper Green Larsen

Explaining the surprising generalization performance of deep neural networks is an active and important line of research in theoretical machine learning. Influential work by Arora et al. (ICML'18) showed that, noise stab…

BIG-bench Machine LearningGeneralization Bounds

On Tighter Generalization Bounds for Deep Neural Networks: CNNs, ResNets, and Beyond

2019-05-01 · ICLR 2019 5 · Xingguo Li, Junwei Lu, Zhaoran Wang, Jarvis Haupt 외

We propose a generalization error bound for a general family of deep neural networks based on the depth and width of the networks, as well as the spectral norm of weight matrices. Through introducing a novel characteriza…

Generalization Bounds

On Tighter Generalization Bound for Deep Neural Networks: CNNs, ResNets, and Beyond

2018-06-13 · Xingguo Li, Junwei Lu, Zhaoran Wang, Jarvis Haupt 외

We establish a margin based data dependent generalization error bound for a general family of deep neural networks in terms of the depth and width, as well as the Jacobian of the networks. Through introducing a new chara…

Generalization Bounds

Generalization Bounds for Magnitude-Based Pruning via Sparse Matrix Sketching

2023-05-30 · Etash Kumar Guha, Prasanjit Dubey, Xiaoming Huo

In this paper, we derive a novel bound on the generalization error of Magnitude-Based pruning of overparameterized neural networks. Our work builds on the bounds in Arora et al. [2018] where the error depends on one, the…

Generalization Bounds

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

2020-02-23 · Yossi Adi, Yaniv Nemcovsky, Alex Schwing, Tamir Hazan

Generalization bounds which assess the difference between the true risk and the empirical risk have been studied extensively. However, to obtain bounds, current techniques use strict assumptions such as a uniformly bound…

General ClassificationGeneralization BoundsMulti-class Classification