English
Related papers

Related papers: A unified framework for information-theoretic gene…

200 papers

Despite its empirical success, deep learning still lacks a comprehensive theoretical understanding of model fitting and generalization. This paper proposes the probability distribution (PD) learning framework to analyze the optimization and…

Machine Learning · Computer Science 2025-10-09 Binchuan Qi , Wei Gong , Li Li

In recent years, inconsistency in Bayesian deep learning has attracted significant attention. Tempered or generalized posterior distributions are frequently employed as direct and effective solutions. Nonetheless, the underlying mechanisms…

Machine Learning · Computer Science 2025-09-23 Yinsong Chen , Samson S. Yu , Zhong Li , Chee Peng Lim

We establish in-expectation and tail bounds on the generalization error of representation learning type algorithms. The bounds are in terms of the relative entropy between the distribution of the representations extracted from the training…

Machine Learning · Statistics 2025-03-21 Milad Sefidgaran , Abdellatif Zaidi , Piotr Krasnowski

In transfer learning, training and testing data sets are drawn from different data distributions. The transfer generalization gap is the difference between the population loss on the target data distribution and the training loss. The…

Machine Learning · Computer Science 2021-01-26 Sharu Theresa Jose , Osvaldo Simeone

This paper introduces a new technique for quantifying the approximation error of a broad class of probabilistic inference programs, including ones based on both variational and Monte Carlo approaches. The key idea is to derive a subjective…

Artificial Intelligence · Computer Science 2016-06-02 Marco F Cusumano-Towner , Vikash K Mansinghka

We provide an information-theoretic framework for studying the generalization properties of machine learning algorithms. Our framework ties together existing approaches, including uniform convergence bounds and recent methods for adaptive…

Machine Learning · Computer Science 2020-06-22 Thomas Steinke , Lydia Zakynthinou

We present a unified information-theoretic framework elucidating the interplay between stability, privacy, and the generalization performance of quantum learning algorithms. We establish a bound on the expected generalization error in terms…

Quantum Physics · Physics 2026-02-06 Ayanava Dasgupta , Naqueeb Ahmad Warsi , Masahito Hayashi

We derive generalization error bounds for the training of two-layer neural networks without assuming boundedness of the loss function, using Wasserstein distance estimates on the discrepancy between a probability distribution and its…

Machine Learning · Statistics 2026-04-09 Jiang Yu Nguwi , Nicolas Privault

Meta-learning optimizes an inductive bias---typically in the form of the hyperparameters of a base-learning algorithm---by observing data from a finite number of related tasks. This paper presents an information-theoretic bound on the…

Machine Learning · Computer Science 2021-02-09 Arezou Rezazadeh , Sharu Theresa Jose , Giuseppe Durisi , Osvaldo Simeone

In this paper, the method of gaps, a technique for deriving closed-form expressions in terms of information measures for the generalization error of supervised machine learning algorithms is introduced. The method relies on the notion of…

Machine Learning · Computer Science 2026-01-01 Samir M. Perlaza , Xinying Zou

Despite substantial progress in promoting fairness in high-stake applications using machine learning models, existing methods often modify the training process, such as through regularizers or other interventions, but lack formal guarantees…

Machine Learning · Computer Science 2025-06-10 Firas Laakom , Haobo Chen , Jürgen Schmidhuber , Yuheng Bu

In this paper, we develop a general machinery for finding explicit uniform probability and moment bounds on sub-additive positive functionals of random processes. Using the developed general technique, we derive uniform bounds on the…

Probability · Mathematics 2012-02-09 Alexander Goldenshluger , Oleg Lepski

This paper focuses on parameter estimation and introduces a new method for lower bounding the Bayesian risk. The method allows for the use of virtually \emph{any} information measure, including R\'enyi's $\alpha$, $\varphi$-Divergences, and…

Information Theory · Computer Science 2023-03-27 Amedeo Roberto Esposito , Adrien Vandenbroucque , Michael Gastpar

Off-policy learning (OPL) often involves minimizing a risk estimator based on importance weighting to correct bias from the logging policy used to collect data. However, this method can produce an estimator with a high variance. A common…

Machine Learning · Computer Science 2024-06-06 Imad Aouali , Victor-Emmanuel Brunel , David Rohde , Anna Korba

The present paper provides a new generic strategy leading to non-asymptotic theoretical guarantees on the Leave-one-Out procedure applied to a broad class of learning algorithms. This strategy relies on two main ingredients: the new notion…

Machine Learning · Statistics 2016-08-24 Alain Celisse , Benjamin Guedj

In this paper, we provide a new framework to obtain the generalization bounds of the learning process for domain adaptation, and then apply the derived bounds to analyze the asymptotical convergence of the learning process. Without loss of…

Machine Learning · Computer Science 2013-04-08 Chao Zhang , Lei Zhang , Jieping Ye

As machine learning applications grow increasingly ubiquitous and complex, they face an increasing set of requirements beyond accuracy. The prevalent approach to handle this challenge is to aggregate a weighted combination of requirement…

Machine Learning · Computer Science 2026-01-07 Aneesh Barthakur , Luiz F. O. Chamon

Understanding the generalization abilities of modern machine learning algorithms has been a major research topic over the past decades. In recent years, the learning dynamics of Stochastic Gradient Descent (SGD) have been related to…

Machine Learning · Statistics 2023-12-04 Benjamin Dupuis , Paul Viallard

The sample compression theory provides generalization guarantees for predictors that can be fully defined using a subset of the training dataset and a (short) message string, generally defined as a binary sequence. Previous works provided…

Machine Learning · Computer Science 2025-03-12 Mathieu Bazinet , Valentina Zantedeschi , Pascal Germain

Machine unlearning refers to mechanisms that can remove the influence of a subset of training data upon request from a trained model without incurring the cost of re-training from scratch. This paper develops a unified PAC-Bayesian…

Machine Learning · Computer Science 2021-06-02 Sharu Theresa Jose , Osvaldo Simeone