Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates
In this work, we improve upon the stepwise analysis of noisy iterative learning algorithms initiated by Pensia, Jog, and Loh (2018) and recently extended by Bu, Zou, and Veeravalli (2019). Our main contributions are significantly improved mutual information bounds for Stochastic Gradient Langevin Dynamics via data-dependent estimates. Our approach is based on the variational characterization of mutual information and the use of data-dependent priors that forecast the mini-batch gradient based on a subset of the training samples. Our approach is broadly applicable within the information-theoretic framework of Russo and Zou (2015) and Xu and Raginsky (2017). Our bound can be tied to a measure of flatness of the empirical risk surface. As compared with other bounds that depend on the squared norms of gradients, empirical investigations show that the terms in our bounds are orders of magnitude smaller.
Code (1)
Tasks
Generalization BoundsSimilar Papers 제목 키워드 기반
Time-Independent Information-Theoretic Generalization Bounds for SGLD
We provide novel information-theoretic generalization bounds for stochastic gradient Langevin dynamics (SGLD) under the assumptions of smoothness and dissipativity, which are widely used in sampling and non-convex optimi…
Generalization BoundsOptimizing Information-theoretical Generalization Bounds via Anisotropic Noise in SGLD
Recently, the information-theoretical framework has been proven to be able to obtain non-vacuous generalization bounds for large models trained by Stochastic Gradient Langevin Dynamics (SGLD) with isotropic noise. In thi…
Generalization BoundsOptimizing Information-theoretical Generalization Bound via Anisotropic Noise of SGLD
Recently, the information-theoretical framework has been proven to be able to obtain non-vacuous generalization bounds for large models trained by Stochastic Gradient Langevin Dynamics (SGLD) with isotropic noise. In th…
Generalization BoundsCharacterizing Membership Privacy in Stochastic Gradient Langevin Dynamics
Bayesian deep learning is recently regarded as an intrinsic way to characterize the weight uncertainty of deep neural networks~(DNNs). Stochastic Gradient Langevin Dynamics~(SGLD) is an effective method to enable Bayesia…
Deep LearningGeneralization BoundsUnderstanding the Generalization Ability of Deep Learning Algorithms: A Kernelized Renyi's Entropy Perspective
Recently, information theoretic analysis has become a popular framework for understanding the generalization behavior of deep neural networks. It allows a direct analysis for stochastic gradient/Langevin descent (SGD/SGL…