paper-with-me

홈 › Papers

A Probabilistic Representation of DNNs: Bridging Mutual Information and Generalization

2021-06-18 · Xinjie Lan, Kenneth Barner

Recently, Mutual Information (MI) has attracted attention in bounding the generalization error of Deep Neural Networks (DNNs). However, it is intractable to accurately estimate the MI in DNNs, thus most previous works have to relax the MI bound, which in turn weakens the information theoretic explanation for generalization. To address the limitation, this paper introduces a probabilistic representation of DNNs for accurately estimating the MI. Leveraging the proposed MI estimator, we validate the information theoretic explanation for generalization, and derive a tighter generalization bound than the state-of-the-art relaxations.

📄 PDF Abstract BibTeX arXiv:2106.10262

Code (1)

EthanLan/A-Tighter-Genearlization-Bound-in-deep-learning 공식 구현 tf

Similar Papers 제목 키워드 기반

A Probabilistic Representation for Deep Learning: Delving into The Information Bottleneck Principle

2021-05-21 · NeurIPS 2021 12 · Xinjie Lan, Kenneth Barner

The Information Bottleneck (IB) principle has recently attracted great attention to explaining Deep Neural Networks (DNNs), and the key is to accurately estimate the mutual information between a hidden layer and dataset.…

Estimating Information Flow in DNNs

2019-05-01 · ICLR 2019 5 · Ziv Goldfeld, Ewout van den Berg, Kristjan Greenewald, Brian Kingsbury 외

We study the evolution of internal representations during deep neural network (DNN) training, aiming to demystify the compression aspect of the information bottleneck theory. The theory suggests that DNN training compris…

Clustering

Probabilistic modeling the hidden layers of deep neural networks

2019-09-25 · Xinjie Lan, Kenneth E. Barner

In this paper, we demonstrate that the parameters of Deep Neural Networks (DNNs) cannot satisfy the i.i.d. prior assumption and activations being i.i.d. is not valid for all the hidden layers of DNNs. Hence, the Gaussian…

valid

Tighter Bounds on the Information Bottleneck with Application to Deep Learning

2024-02-12 · Nir Weingarten, Zohar Yakhini, Moshe Butman, Ran Gilad-Bachrach

Deep Neural Nets (DNNs) learn latent representations induced by their downstream task, objective function, and other parameters. The quality of the learned representations impacts the DNN's generalization ability and the…

Adversarial RobustnessDeep Learning

A Probabilistic Representation of Deep Learning

2019-08-26 · Xinjie Lan, Kenneth E. Barner

In this work, we introduce a novel probabilistic representation of deep learning, which provides an explicit explanation for the Deep Neural Networks (DNNs) in three aspects: (i) neurons define the energy of a Gibbs dist…

Deep Learning