English
Related papers

Related papers: Learning curves for the multi-class teacher-studen…

200 papers

We investigate the generalization ability of a simple perceptron trained in the off-line and on-line supervised modes. Examples are extracted from the teacher who is a non-monotonic perceptron. For this system, difficulties of training can…

Disordered Systems and Neural Networks · Physics 2008-02-03 Jun-ichi Inoue , Hidetoshi Nishimori , Yoshiyuki Kabashima

We study a natural extension of classical empirical risk minimization, where the hypothesis space is a random subspace of a given space. In particular, we consider possibly data dependent subspaces spanned by a random subset of the data,…

Machine Learning · Statistics 2022-12-09 Andrea Della Vecchia , Ernesto De Vito , Lorenzo Rosasco

As modern machine learning models continue to advance the computational frontier, it has become increasingly important to develop precise estimates for expected performance improvements under different model and data scaling regimes.…

Machine Learning · Computer Science 2023-06-13 Lechao Xiao , Hong Hu , Theodor Misiakiewicz , Yue M. Lu , Jeffrey Pennington

Classification has been a major task for building intelligent systems as it enables decision-making under uncertainty. Classifier design aims at building models from training data for representing feature-label distributions--either…

Machine Learning · Statistics 2023-01-31 Omar Maddouri , Xiaoning Qian , Francis J. Alexander , Edward R. Dougherty , Byung-Jun Yoon

We present a closed form expression for initializing the input weights in a multi-layer perceptron, which can be used as the first step in synthesis of an Extreme Learning Ma-chine. The expression is based on the standard function for a…

Neural and Evolutionary Computing · Computer Science 2014-06-12 Jonathan Tapson , Philip de Chazal , André van Schaik

We propose a unified framework for global-local regularization that bridges the gap between classical techniques -- such as ridge regression and the nonnegative garotte -- and modern Bayesian hierarchical modeling. By estimating local…

Methodology · Statistics 2025-12-17 Jyotishka Datta , Nick Polson , Vadim Sokolov

Studies on generalization performance of machine learning algorithms under the scope of information theory suggest that compressed representations can guarantee good generalization, inspiring many compression-based regularization methods.…

Machine Learning · Computer Science 2019-10-16 Antoine Saporta , Yifu Chen , Michael Blot , Matthieu Cord

It is increasingly common in machine learning to use learned models to label data and then employ such data to train more capable models. The phenomenon of weak-to-strong generalization exemplifies the advantage of this two-stage procedure:…

Machine Learning · Computer Science 2026-05-26 Diyuan Wu , Lehan Chen , Theodor Misiakiewicz , Marco Mondelli

Empirical studies of trained models often report a transient regime in which signal is detectable in a finite gradient descent time window before overfitting dominates. We provide an analytically tractable random-matrix model that…

Machine Learning · Statistics 2026-04-21 Florentin Coeurdoux , Grégoire Ferré , Jean-Philippe Bouchaud

Due to their flexibility and predictive performance, machine-learning based regression methods have become an important tool for predictive modeling and forecasting. However, most methods focus on estimating the conditional mean or specific…

Machine Learning · Statistics 2019-03-15 Rui Li , Howard D. Bondell , Brian J. Reich

Extreme learning machine (ELM) is a network model that arbitrarily initializes the first hidden layer and can be computed speedily. In order to improve the classification performance of ELM, a $\ell_2$ and $\ell_{0.5}$ regularization ELM…

Optimization and Control · Mathematics 2023-01-05 Liangjuan Zhou , Wei Miao

We study the implicit bias of optimization in robust empirical risk minimization (robust ERM) and its connection with robust generalization. In classification settings under adversarial perturbations with linear models, we study what type…

Machine Learning · Computer Science 2024-06-10 Nikolaos Tsilivis , Natalie Frank , Nathan Srebro , Julia Kempe

In this paper, we propose a general framework to learn a robust large-margin binary classifier when corrupt measurements, called anomalies, caused by sensor failure might be present in the training set. The goal is to minimize the…

Machine Learning · Computer Science 2016-11-17 Tianpei Xie , Nasser M. Nasrabadi , Alfred O. Hero

In this paper, we study the learning rate of generalized Bayes estimators in a general setting where the hypothesis class can be uncountable and have an irregular shape, the loss function can have heavy tails, and the optimal hypothesis may…

Statistics Theory · Mathematics 2021-11-22 Lam Si Tung Ho , Binh T. Nguyen , Vu Dinh , Duy Nguyen

It has been recognized that the diversity of base learners is of utmost importance to a good ensemble. This paper defines a novel measurement of diversity, termed as exclusivity. With the designed exclusivity, we further propose an ensemble…

Machine Learning · Computer Science 2016-05-17 Xiaojie Guo

Bayesian Reinforcement Learning (RL) is capable of not only incorporating domain knowledge, but also solving the exploration-exploitation dilemma in a natural way. As Bayesian RL is intractable except for special cases, previous work has…

Artificial Intelligence · Computer Science 2013-06-14 Kenji Kawaguchi , Mauricio Araya

Neural networks trained to minimize the logistic (a.k.a. cross-entropy) loss with gradient-based methods are observed to perform well in many supervised classification tasks. Towards understanding this phenomenon, we analyze the training…

Optimization and Control · Mathematics 2020-06-23 Lenaic Chizat , Francis Bach

Efficient feature selection from high-dimensional datasets is a very important challenge in many data-driven fields of science and engineering. We introduce a statistical mechanics inspired strategy that addresses the problem of sparse…

Machine Learning · Statistics 2021-04-07 Alfredo Braunstein , Thomas Gueudré , Andrea Pagnani , Mirko Pieropan

Understanding the generalization properties of neural networks on simple input-output distributions is key to explaining their performance on real datasets. The classical teacher-student setting, where a network is trained on data generated…

Disordered Systems and Neural Networks · Physics 2026-03-26 Rodrigo Pérez Ortiz , Gibbs Nwemadji , Jean Barbier , Federica Gerace , Alessandro Ingrosso , Clarissa Lauditi , Enrico M. Malatesta

We consider the minimum error entropy (MEE) criterion and an empirical risk minimization learning algorithm in a regression setting. A learning theory approach is presented for this MEE algorithm and explicit error bounds are provided in…

Machine Learning · Computer Science 2013-02-26 Ting Hu , Jun Fan , Qiang Wu , Ding-Xuan Zhou