English
Related papers

Related papers: Understanding Generalization via Leave-One-Out Con…

200 papers

A recent line of works, initiated by Russo and Xu, has shown that the generalization error of a learning algorithm can be upper bounded by information measures. In most of the relevant works, the convergence rate of the expected…

Information Theory · Computer Science 2022-05-16 Xuetong Wu , Jonathan H. Manton , Uwe Aickelin , Jingge Zhu

Mutual information has been successfully adopted in filter feature-selection methods to assess both the relevancy of a subset of features in predicting the target variable and the redundancy with respect to other variables. However,…

Machine Learning · Computer Science 2019-07-18 Mario Beraha , Alberto Maria Metelli , Matteo Papini , Andrea Tirinzoni , Marcello Restelli

Maximum mutual information (MMI) is a model selection criterion used for hidden Markov model (HMM) parameter estimation that was developed more than twenty years ago as a discriminative alternative to the maximum likelihood criterion for…

Computation and Language · Computer Science 2010-02-04 Steven Wegmann

The data for many classification problems, such as pattern and speech recognition, follow mixture distributions. To quantify the optimum performance for classification tasks, the Shannon mutual information is a natural information-theoretic…

Signal Processing · Electrical Eng. & Systems 2022-06-22 Yijun Ding , Amit Ashok

We study conformal prediction in the one-shot federated learning setting. The main goal is to compute marginally and training-conditionally valid prediction sets, at the server-level, in only one round of communication between the agents…

Statistics Theory · Mathematics 2024-05-22 Pierre Humbert , Batiste Le Bars , Aurélien Bellet , Sylvain Arlot

In risk-sensitive learning, one aims to find a hypothesis that minimizes a risk-averse (or risk-seeking) measure of loss, instead of the standard expected loss. In this paper, we propose to study the generalization properties of…

Machine Learning · Statistics 2021-01-05 Jaeho Lee , Sejun Park , Jinwoo Shin

Meta-learning automatically infers an inductive bias by observing data from a number of related tasks. The inductive bias is encoded by hyperparameters that determine aspects of the model class or training algorithm, such as initialization…

Machine Learning · Computer Science 2020-11-10 Sharu Theresa Jose , Osvaldo Simeone , Giuseppe Durisi

Mutual information (MI) is a fundamental quantity in information theory and machine learning. However, direct estimation of MI is intractable, even if the true joint probability density for the variables of interest is known, as it involves…

Machine Learning · Computer Science 2024-04-29 Rob Brekelmans , Sicong Huang , Marzyeh Ghassemi , Greg Ver Steeg , Roger Grosse , Alireza Makhzani

We study prediction and estimation problems using empirical risk minimization, relative to a general convex loss function. We obtain sharp error rates even when concentration is false or is very restricted, for example, in heavy-tailed…

Machine Learning · Statistics 2014-10-14 Shahar Mendelson

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

We propose a novel framework for exploring weak and $L_2$ generalization errors of algorithms through the lens of differential calculus on the space of probability measures. Specifically, we consider the KL-regularized empirical risk…

Machine Learning · Statistics 2023-06-21 Gholamali Aminian , Samuel N. Cohen , Łukasz Szpruch

Decentralized learning offers privacy and communication efficiency when data are naturally distributed among agents communicating over an underlying graph. Motivated by overparameterized learning settings, in which models are trained to…

Machine Learning · Computer Science 2023-03-28 Hossein Taheri , Christos Thrampoulidis

In safety-critical classification, the cost of failure is often asymmetric, yet Bayesian deep learning summarises epistemic uncertainty with a single scalar, mutual information (MI), that cannot distinguish whether a model's ignorance…

Machine Learning · Statistics 2026-02-27 Mame Diarra Toure , David A. Stephens

We study prediction intervals based on leave-one-out residuals in a linear regression model where the number of explanatory variables can be large compared to sample size. We establish uniform asymptotic validity (conditional on the…

Statistics Theory · Mathematics 2016-02-19 Lukas Steinberger , Hannes Leeb

Recent advances in statistical learning theory have revealed profound connections between mutual information (MI) bounds, PAC-Bayesian theory, and Bayesian nonparametrics. This work introduces a novel mutual information bound for…

Machine Learning · Statistics 2025-08-18 El Mahdi Khribch , Pierre Alquier

In this paper, we provide new theoretical results on the generalization properties of learning algorithms for multiclass classification problems. The originality of our work is that we propose to use the confusion matrix of a classifier as…

Machine Learning · Computer Science 2012-05-25 Pierre Machart , Liva Ralaivola

We adopt an information-theoretic framework to analyze the generalization behavior of the class of iterative, noisy learning algorithms. This class is particularly suitable for study under information-theoretic metrics as the algorithms are…

Machine Learning · Computer Science 2023-07-20 Ibrahim Issa , Amedeo Roberto Esposito , Michael Gastpar

We aim to discover manipulation concepts embedded in the unannotated demonstrations, which are recognized as key physical states. The discovered concepts can facilitate training manipulation policies and promote generalization. Current…

Robotics · Computer Science 2024-07-23 Pei Zhou , Yanchao Yang

Catastrophic forgetting of connectionist neural networks is caused by the global sharing of parameters among all training examples. In this study, we analyze parameter sharing under the conditional computation framework where the parameters…

Machine Learning · Computer Science 2019-06-18 Min Lin , Jie Fu , Yoshua Bengio

In the algorithm selection research, the discussion surrounding algorithm features has been significantly overshadowed by the emphasis on problem features. Although a few empirical studies have yielded evidence regarding the effectiveness…

Machine Learning · Computer Science 2024-06-04 Xingyu Wu , Yan Zhong , Jibin Wu , Yuxiao Huang , Sheng-hao Wu , Kay Chen Tan