中文
相关论文

相关论文: Asymmetry of the Relative Entropy in the Regulariz…

200 篇论文

The effect of the relative entropy asymmetry is analyzed in the empirical risk minimization with relative entropy regularization (ERM-RER) problem. A novel regularization is introduced, coined Type-II regularization, that allows for…

信息论 · 计算机科学 2023-06-13 Francisco Daunas , Iñaki Esnaola , Samir M. Perlaza , H. Vincent Poor

The optimality and sensitivity of the empirical risk minimization problem with relative entropy regularization (ERM-RER) are investigated for the case in which the reference is a sigma-finite measure instead of a probability measure. This…

机器学习 · 计算机科学 2022-11-15 Samir M. Perlaza , Gaetan Bisson , Iñaki Esnaola , Alain Jean-Marie , Stefano Rini

The empirical risk minimization (ERM) problem with relative entropy regularization (ERM-RER) is investigated under the assumption that the reference measure is a $\sigma$-finite measure, and not necessarily a probability measure. Under this…

统计理论 · 数学 2024-04-09 Samir M. Perlaza , Gaetan Bisson , Iñaki Esnaola , Alain Jean-Marie , Stefano Rini

The solution to empirical risk minimization with $f$-divergence regularization (ERM-$f$DR) is presented under mild conditions on $f$. Under such conditions, the optimal measure is shown to be unique. Examples of the solution for particular…

机器学习 · 统计学 2024-10-25 Francisco Daunas , Iñaki Esnaola , Samir M. Perlaza , H. Vincent Poor

Recently, invariant risk minimization (IRM) was proposed as a promising solution to address out-of-distribution (OOD) generalization. However, it is unclear when IRM should be preferred over the widely-employed empirical risk minimization…

机器学习 · 计算机科学 2022-08-22 Kartik Ahuja , Jun Wang , Amit Dhurandhar , Karthikeyan Shanmugam , Kush R. Varshney

In this paper, the solution to the empirical risk minimization problem with $f$-divergence regularization (ERM-$f$DR) is presented and conditions under which the solution also serves as the solution to the minimization of the expected…

机器学习 · 统计学 2026-01-21 Francisco Daunas , Iñaki Esnaola , Samir M. Perlaza , H. Vincent Poor

We consider the random design regression model with square loss. We propose a method that aggregates empirical minimizers (ERM) over appropriately chosen random subsets and reduces to ERM in the extreme case, and we establish sharp oracle…

统计理论 · 数学 2017-07-04 Alexander Rakhlin , Karthik Sridharan , Alexandre B. Tsybakov

We study robust linear regression in high-dimension, when both the dimension $d$ and the number of data points $n$ diverge with a fixed ratio $\alpha=n/d$, and study a data model that includes outliers. We provide exact asymptotics for the…

机器学习 · 统计学 2024-06-24 Matteo Vilucchio , Emanuele Troiani , Vittorio Erba , Florent Krzakala

The de-facto standard approach of promoting sparsity by means of $\ell_1$-regularization becomes ineffective in the presence of simplex constraints, i.e.,~the target is known to have non-negative entries summing up to a given constant. The…

统计方法学 · 统计学 2016-05-04 Ping Li , Syama Sundar Rangapuram , Martin Slawski

This article develops a general theory for minimum norm interpolating estimators and regularized empirical risk minimizers (RERM) in linear models in the presence of additive, potentially adversarial, errors. In particular, no conditions on…

统计理论 · 数学 2021-10-08 Geoffrey Chinot , Matthias Löffler , Sara van de Geer

Entropy integrals are widely used as a powerful empirical process tool to obtain upper bounds for the rates of convergence of global empirical risk minimizers (ERMs), in standard settings such as density estimation and regression. The upper…

统计理论 · 数学 2021-01-08 Qiyang Han

Existing training criteria in automatic speech recognition(ASR) permit the model to freely explore more than one time alignments between the feature and label sequences. In this paper, we use entropy to measure a model's uncertainty, i.e.…

计算与语言 · 计算机科学 2022-12-26 Ehsan Variani , Ke Wu , David Rybach , Cyril Allauzen , Michael Riley

Reinforcement learning (RL) has become a key approach for enhancing reasoning in large language models (LLMs), yet scalable training is often hindered by the rapid collapse of policy entropy, which leads to premature convergence and…

机器学习 · 计算机科学 2026-04-14 Ming Lei , Christophe Baehr

We study the minimal error of the Empirical Risk Minimization (ERM) procedure in the task of regression, both in the random and the fixed design settings. Our sharp lower bounds shed light on the possibility (or impossibility) of adapting…

统计理论 · 数学 2021-02-25 Gil Kur , Alexander Rakhlin

This guide provides a reference for high-probability regret bounds in empirical risk minimization (ERM). The presentation is modular: we begin with intuition and general proof strategies, then state broadly applicable guarantees under…

机器学习 · 统计学 2026-03-04 Lars van der Laan

State entropy regularization has empirically shown better exploration and sample complexity in reinforcement learning (RL). However, its theoretical guarantees have not been studied. In this paper, we show that state entropy regularization…

机器学习 · 计算机科学 2025-12-02 Yonatan Ashlag , Uri Koren , Mirco Mutti , Esther Derman , Pierre-Luc Bacon , Shie Mannor

A risk measure that is consistent with the second-order stochastic dominance and additive for sums of independent random variables can be represented as a weighted entropic risk measure (WERM). The expected utility maximization problem with…

数理金融 · 定量金融 2021-12-07 Jianming Xia

The dual formulation of empirical risk minimization with f-divergence regularization (ERM-fDR) is introduced. The solution of the dual optimization problem to the ERM-fDR is connected to the notion of normalization function introduced as an…

机器学习 · 统计学 2025-08-06 Francisco Daunas , Iñaki Esnaola , Samir M. Perlaza

In this work we investigate to which extent one can recover class probabilities within the empirical risk minimization (ERM) paradigm. The main aim of our paper is to extend existing results and emphasize the tight relations between…

机器学习 · 计算机科学 2020-07-22 Alexander Mey , Marco Loog

The solution to empirical risk minimization with $f$-divergence regularization (ERM-$f$DR) is extended to constrained optimization problems, establishing conditions for equivalence between the solution and constraints. A dual formulation of…

机器学习 · 统计学 2025-02-21 Francisco Daunas , Iñaki Esnaola , Samir M. Perlaza , Gholamali Aminian
‹ 上一页 1 2 3 10 下一页 ›