paper-with-me

Papers

Information-theoretic generalization bounds for black-box learning algorithms

2021-10-04 · NeurIPS 2021 12 · Hrayr Harutyunyan, Maxim Raginsky, Greg Ver Steeg, Aram Galstyan

We derive information-theoretic generalization bounds for supervised learning algorithms based on the information contained in predictions rather than in the output of the training algorithm. These bounds improve over the existing information-theoretic bounds, are applicable to a wider range of algorithms, and solve two key challenges: (a) they give meaningful results for deterministic algorithms and (b) they are significantly easier to estimate. We show experimentally that the proposed bounds closely follow the generalization gap in practical scenarios for deep learning.

📄 PDF Abstract BibTeX arXiv:2110.01584

Code (1)

hrayrhar/f-cmi 공식 구현 pytorch

Tasks

Generalization Bounds

Similar Papers 제목 키워드 기반

On Leave-One-Out Conditional Mutual Information For Generalization

2022-07-01 · Mohamad Rida Rammal, Alessandro Achille, Aditya Golatkar, Suhas Diggavi 외

We derive information theoretic generalization bounds for supervised learning algorithms based on a new measure of leave-one-out conditional mutual information (loo-CMI). Contrary to other CMI bounds, which are black-box…

Generalization Boundsimage-classificationImage Classification

Information Theoretic Lower Bounds for Information Theoretic Upper Bounds

2023-02-09 · NeurIPS 2023 11 · Roi Livni

We examine the relationship between the mutual information between the output model and the empirical sample and the generalization of the algorithm in the context of stochastic convex optimization. Despite increasing in…

Generalization Bounds

Tighter Information-Theoretic Generalization Bounds from Supersamples

2023-02-05 · Ziqiao Wang, Yongyi Mao

In this work, we present a variety of novel information-theoretic generalization bounds for learning algorithms, from the supersample setting of Steinke & Zakynthinou (2020)-the setting of the "conditional mutual informa…

Generalization Bounds

Towards Sharper Information-theoretic Generalization Bounds for Meta-Learning

2025-01-26 · Wen Wen, Tieliang Gong, Yuxin Dong, Yong-Jin Liu 외

In recent years, information-theoretic generalization bounds have emerged as a promising approach for analyzing the generalization capabilities of meta-learning algorithms. However, existing results are confined to two-s…

Generalization BoundsMeta-Learning

Information-theoretic analysis of generalization capability of learning algorithms

2017-05-22 · NeurIPS 2017 12 · Aolin Xu, Maxim Raginsky

We derive upper bounds on the generalization error of a learning algorithm in terms of the mutual information between its input and output. The bounds provide an information-theoretic understanding of generalization in l…