Risk minimization by median-of-means tournaments

DOI10.4171/JEMS/937zbMath1436.62312arXiv1608.00757OpenAlexW2995540461MaRDI QIDQ2302852

Shahar Mendelson, Gábor Lugosi

Publication date: 26 February 2020

Published in: Journal of the European Mathematical Society (JEMS) (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1608.00757

zbMATH Keywords

heavy-tailed distributionsempirical risk minimizationmedian of means estimator

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Linear regression; mixed models (62J05) Statistics of extreme values; tail inference (62G32) General nonlinear regression (62J02) Prediction theory (aspects of stochastic processes) (60G25) Paired and multiple comparisons; multiple testing (62J15)

Related Items

On least squares estimation under heteroscedastic and heavy-tailed errors, A New Principle for Tuning-Free Huber Regression, All-in-one robust estimator of the Gaussian mean, Optimal robust mean and location estimation via convex programs with respect to any pseudo-norms, Robust statistical learning with Lipschitz and convex loss functions, Unnamed Item, Topics in robust statistical learning, Robust machine learning by median-of-means: theory and practice, Robust regression using biased objectives, Robust classification via MOM minimization, Extending the scope of the small-ball method, Unnamed Item, Solvable integration problems and optimal sample size selection, Learning from MOM's principles: Le Cam's approach, Algorithms of robust stochastic optimization based on mirror descent method, A MOM-based ensemble method for robustness, subsampling and hyperparameter tuning, Iteratively reweighted \(\ell_1\)-penalized robust regression, K-bMOM: A robust Lloyd-type clustering algorithm based on bootstrap median-of-means, The smallest singular value of heavy-tailed not necessarily i.i.d. random matrices via random rounding, Finite sample properties of parametric MMD estimation: robustness to misspecification and dependence, On Monte-Carlo methods in convex stochastic optimization, Unnamed Item, Suboptimality of constrained least squares and improvements via non-linear predictors, Distribution-free robust linear regression