English
Related papers

Related papers: Rethinking generalization of classifiers in separa…

200 papers

Learning from quantum data presents new challenges to the paradigm of learning from data. This typically entails the use of quantum learning models to learn quantum processes that come with enough subtleties to modify the theoretical…

Quantum Physics · Physics 2025-09-01 Yixian Qiu , Lirandë Pira , Patrick Rebentrost

We consider the problem of training a classification model with group annotated training data. Recent work has established that, if there is distribution shift across different groups, models trained using the standard empirical risk…

Machine Learning · Computer Science 2022-04-21 Vihari Piratla , Praneeth Netrapalli , Sunita Sarawagi

We propose a general theorem providing upper bounds for the risk of an empirical risk minimizer (ERM).We essentially focus on the binary classification framework. We extend Tsybakov's analysis of the risk of an ERM under margin type…

Statistics Theory · Mathematics 2016-08-14 Pascal Massart , Élodie Nédélec

Overparameterized deep networks have the capacity to memorize training data with zero \emph{training error}. Even after memorization, the \emph{training loss} continues to approach zero, making the model overconfident and the test…

Machine Learning · Computer Science 2021-04-01 Takashi Ishida , Ikko Yamane , Tomoya Sakai , Gang Niu , Masashi Sugiyama

We give a general result concerning the rates of convergence of penalized empirical risk minimizers (PERM) in the regression model. Then, we consider the problem of agnostic learning of the regression, and give in this context an oracle…

Statistics Theory · Mathematics 2008-10-30 S. Gaïffas , G. Lecué

We study the scaling of classification error rates with respect to the size of the training dataset. In contrast to classical results where rates are minimax optimal for a problem class, this work starts with the empirical observation that,…

Machine Learning · Statistics 2025-06-04 Pengkun Yang , Jingzhao Zhang

In order to circumvent statistical and computational hardness results in sequential decision-making, recent work has considered smoothed online learning, where the distribution of data at each time is assumed to have bounded likeliehood…

Machine Learning · Statistics 2024-02-26 Adam Block , Alexander Rakhlin , Abhishek Shetty

Supervised deep learning involves the training of neural networks with a large number $N$ of parameters. For large enough $N$, in the so-called over-parametrized regime, one can essentially fit the training data points. Sparsity-based…

Disordered Systems and Neural Networks · Physics 2020-04-22 Mario Geiger , Arthur Jacot , Stefano Spigler , Franck Gabriel , Levent Sagun , Stéphane d'Ascoli , Giulio Biroli , Clément Hongler , Matthieu Wyart

Plotting a learner's average performance against the number of training samples results in a learning curve. Studying such curves on one or more data sets is a way to get to a better understanding of the generalization properties of this…

Machine Learning · Computer Science 2020-03-16 Marco Loog , Tom Viering , Alexander Mey

We consider the problem of strategic classification, where a learner must build a model to classify agents based on features that have been strategically modified. Previous work in this area has concentrated on the case when the learner is…

Machine Learning · Computer Science 2025-05-19 Jack Geary , Henry Gouk

Predictive performance of machine learning models trained with empirical risk minimization (ERM) can degrade considerably under distribution shifts. The presence of spurious correlations in training datasets leads ERM-trained models to…

Machine Learning · Computer Science 2023-02-08 Simon Roburin , Charles Corbière , Gilles Puy , Nicolas Thome , Matthieu Aubry , Renaud Marlet , Patrick Pérez

The Predictive Normalized Maximum Likelihood (pNML) scheme has been recently suggested for universal learning in the individual setting, where both the training and test samples are individual data. The goal of universal learning is to…

Machine Learning · Computer Science 2020-01-09 Koby Bibas , Yaniv Fogel , Meir Feder

When optimizing over-parameterized models, such as deep neural networks, a large set of parameters can achieve zero training error. In such cases, the choice of the optimization algorithm and its respective hyper-parameters introduces…

Machine Learning · Computer Science 2019-12-06 Gauthier Gidel , Francis Bach , Simon Lacoste-Julien

Ensembles are a straightforward, remarkably effective method for improving the accuracy,calibration, and robustness of models on classification tasks; yet, the reasons that underlie their success remain an active area of research. We build…

Machine Learning · Statistics 2022-06-22 Neha Gupta , Jamie Smith , Ben Adlam , Zelda Mariet

The generalization of machine learning models has a complex dependence on the data, model and learning algorithm. We study train and test performance, as well as the generalization gap given by the mean of their difference over different…

Machine Learning · Statistics 2022-06-29 Carlos A. Gomez-Uribe

The bias-variance trade-off is a central concept in supervised learning. In classical statistics, increasing the complexity of a model (e.g., number of parameters) reduces bias but also increases variance. Until recently, it was commonly…

Machine Learning · Statistics 2022-03-25 Jason W. Rocks , Pankaj Mehta

The scaling law, a cornerstone of Large Language Model (LLM) development, predicts improvements in model performance with increasing computational resources. Yet, while empirically validated, its theoretical underpinnings remain poorly…

Machine Learning · Computer Science 2026-02-03 Chiwun Yang

Understanding and accurately following instructions is critical for large language models (LLMs) to be effective across diverse tasks. In this work, we rigorously examine the key factors that enable models to generalize to unseen…

Computation and Language · Computer Science 2024-10-21 Dylan Zhang , Justin Wang , Francois Charton

We introduce a new approach to probabilistic unsupervised learning based on the recognition-parametrised model (RPM): a normalised semi-parametric hypothesis class for joint distributions over observed and latent variables. Under the key…

Machine Learning · Computer Science 2023-04-21 William I. Walker , Hugo Soulat , Changmin Yu , Maneesh Sahani

Supervised classification techniques use training samples to learn a classification rule with small expected 0-1 loss (error probability). Conventional methods enable tractable learning and provide out-of-sample generalization by using…

Machine Learning · Statistics 2023-08-21 Santiago Mazuelas , Mauricio Romero , Peter Grünwald