English
Related papers

Related papers: Local Rademacher Complexity-based Learning Guarant…

200 papers

We study the fundamental problem of learning with respect to the squared loss in a convex class. The state-of-the-art sample complexity estimates in this setting rely on Rademacher complexities, which are generally difficult to control. We…

Statistics Theory · Mathematics 2025-02-24 Daniel Bartl , Shahar Mendelson

In multi-task learning several related tasks are considered simultaneously, with the hope that by an appropriate sharing of information across tasks, each task may benefit from the others. In the context of learning linear functions for…

Machine Learning · Computer Science 2008-09-12 Laurent Jacob , Francis Bach , Jean-Philippe Vert

Multi-task reinforcement learning trains generalist policies that can execute multiple tasks. While recent years have seen significant progress, existing approaches rarely provide formal performance guarantees, which are indispensable when…

Machine Learning · Computer Science 2026-02-03 Yannik Schnitzer , Mathias Jackermeier , Alessandro Abate , David Parker

In this paper, we study the dynamics of temporal difference learning with neural network-based value function approximation over a general state space, namely, \emph{Neural TD learning}. We consider two practically used algorithms,…

Machine Learning · Computer Science 2021-08-09 Semih Cayci , Siddhartha Satpathi , Niao He , R. Srikant

This paper addresses the problem of learning optimal control policies for systems with uncertain dynamics and high-level control objectives specified as Linear Temporal Logic (LTL) formulas. Uncertainty is considered in the workspace…

Robotics · Computer Science 2024-10-17 Yiannis Kantaros , Jun Wang

Learning an appropriate (dis)similarity function from the available data is a central problem in machine learning, since the success of many machine learning algorithms critically depends on the choice of a similarity function to compare…

Machine Learning · Computer Science 2013-08-30 Zheng-Chu Guo , Yiming Ying

Let $\mathcal{F}$ be a class of measurable functions $f:S\mapsto [0,1]$ defined on a probability space $(S,\mathcal{A},P)$. Given a sample (X_1,...,X_n) of i.i.d. random variables taking values in S with common distribution P, let P_n…

Statistics Theory · Mathematics 2011-11-10 Vladimir Koltchinskii

The local Rademacher complexity framework is one of the most successful general-purpose toolboxes for establishing sharp excess risk bounds for statistical estimators based on the framework of empirical risk minimization. Applying this…

Statistics Theory · Mathematics 2022-02-24 Varun Kanade , Patrick Rebeschini , Tomas Vaskevicius

This paper formalizes a latent variable inference problem we call {\em supervised pattern discovery}, the goal of which is to find sets of observations that belong to a single ``pattern.'' We discuss two versions of the problem and prove…

Machine Learning · Statistics 2014-02-10 Jonathan H. Huggins , Cynthia Rudin

Multi-Task Learning (MTL) enables a single model to learn multiple tasks simultaneously, leveraging knowledge transfer among tasks for enhanced generalization, and has been widely applied across various domains. However, task imbalance…

Machine Learning · Computer Science 2025-10-22 Xiaohan Qin , Xiaoxing Wang , Ning Liao , Junchi Yan

Properly modeling latent image distributions plays an important role in a variety of image-related vision problems. Most exiting approaches aim to formulate this problem as optimization models (e.g., Maximum A Posterior, MAP) with…

Computer Vision and Pattern Recognition · Computer Science 2020-08-26 Risheng Liu , Pan Mu , Jian Chen , Xin Fan , Zhongxuan Luo

A fundamental tool in network information theory is the covering lemma, which lower bounds the probability that there exists a pair of random variables, among a give number of independently generated candidates, falling within a given set.…

Information Theory · Computer Science 2019-04-18 Jingbo Liu , Mohammad H. Yassaee , Sergio Verdú

This paper extends standard results from learning theory with independent data to sequences of dependent data. Contrary to most of the literature, we do not rely on mixing arguments or sequential measures of complexity and derive uniform…

Machine Learning · Computer Science 2023-03-22 Fabien Lauer

Iterative self-improvement fine-tunes an autoregressive large language model (LLM) on reward-verified outputs generated by the LLM itself. In contrast to the empirical success of self-improvement, the theoretical foundation of this…

Machine Learning · Computer Science 2026-03-23 Chenruo Liu , Yijun Dong , Yiqiu Shen , Qi Lei

We propose new bounds on the error of learning algorithms in terms of a data-dependent notion of complexity. The estimates we establish give optimal rates and are based on a local and empirical version of Rademacher averages, in the sense…

Statistics Theory · Mathematics 2007-06-13 Peter L. Bartlett , Olivier Bousquet , Shahar Mendelson

\emph{Kullback-Leibler} (KL) regularization is ubiquitous in reinforcement learning algorithms in the form of \emph{reverse} or \emph{forward} KL. Recent studies have demonstrated $\epsilon^{-1}$-type fast rates for decision making under…

Machine Learning · Computer Science 2026-05-12 Qingyue Zhao , Kaixuan Ji , Heyang Zhao , Quanquan Gu

Numerous capability and safety techniques of Large Language Models (LLMs), including RLHF, automated red-teaming, prompt engineering, and infilling, can be cast as sampling from an unnormalized target distribution defined by a given reward…

Machine Learning · Computer Science 2024-05-01 Stephen Zhao , Rob Brekelmans , Alireza Makhzani , Roger Grosse

One of the main open problems in the theory of multi-category margin classification is the form of the optimal dependency of a guaranteed risk on the number C of categories, the sample size m and the margin parameter gamma. From a practical…

Statistics Theory · Mathematics 2018-12-04 Khadija Musayeva , Fabien Lauer , Yann Guermeur

Algorithm- and data-dependent generalization bounds are required to explain the generalization behavior of modern machine learning algorithms. In this context, there exists information theoretic generalization bounds that involve (various…

Machine Learning · Statistics 2023-07-07 Sarah Sachs , Tim van Erven , Liam Hodgkinson , Rajiv Khanna , Umut Simsekli

Class imbalance poses a significant challenge in classification tasks, where traditional approaches often lead to biased models and unreliable predictions. Undersampling and oversampling techniques have been commonly employed to address…

Machine Learning · Computer Science 2025-10-22 Matt Clifford , Jonathan Erskine , Alexander Hepburn , Raúl Santos-Rodríguez , Dario Garcia-Garcia