paper-with-me

홈 › Papers

On the Minimal Error of Empirical Risk Minimization

2021-02-24 · Gil Kur, Alexander Rakhlin

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 to simplicity of the model generating the data. In the fixed design setting, we show that the error is governed by the global complexity of the entire class. In contrast, in random design, ERM may only adapt to simpler models if the local neighborhoods around the regression function are nearly as complex as the class itself, a somewhat counter-intuitive conclusion. We provide sharp lower bounds for performance of ERM for both Donsker and non-Donsker classes. We also discuss our results through the lens of recent studies on interpolation in overparameterized models.

📄 PDF Abstract BibTeX arXiv:2102.12066

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Minimax Limits of k-Fold Cross-Validation via Majority

2026-05-25 · Ido Nachum, Rüdiger Urbanke, Thomas Weinberger arxiv

We study the mean-squared error of $k$-fold cross-validation as a risk estimator, with particular emphasis on how its accuracy depends on the number of folds $k$. Despite the widespread use of cross-validation, principle…

Binary Classification

A Mosco sufficient condition for intrinsic stability of non-unique convex Empirical Risk Minimization

2026-01-25 · Karim Bounja, Lahcen Laayouni, Abdeljalil Sakat arxiv

Empirical risk minimization (ERM) stability is usually studied via single-valued outputs, while convex non-strict losses yield set-valued minimizers. We identify Painlevé-Kuratowski upper semicontinuity (PK-u.s.c.) as th…

Empirical risk minimization is consistent with the mean absolute percentage error

2015-09-08 · Arnaud De Myttenaere, Bénédicte Le Grand, Fabrice Rossi

We study in this paper the consequences of using the Mean Absolute Percentage Error (MAPE) as a measure of quality for regression models. We show that finding the best model under the MAPE is equivalent to doing weighted…

regression

Diametrical Risk Minimization: Theory and Computations

2019-10-24 · Matthew Norton, Johannes O. Royset

The theoretical and empirical performance of Empirical Risk Minimization (ERM) often suffers when loss functions are poorly behaved with large Lipschitz moduli and spurious sharp minimizers. We propose and analyze a coun…

Generalization Bounds

Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning

2021-03-25 · Yaqi Duan, Chi Jin, Zhiyuan Li

This paper considers batch Reinforcement Learning (RL) with general value function approximation. Our study investigates the minimal assumptions to reliably estimate/minimize Bellman error, and characterizes the generali…

Learning Theoryreinforcement-learningReinforcement LearningReinforcement Learning (RL)