Loss minimization and parameter estimation with heavy tails

zbMATH Open1360.62380arXiv1307.1827MaRDI QIDQ2810786FDOQ2810786

Authors: Daniel Hsu, Sivan Sabato 

Publication date: 6 June 2016

Published in: Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1307.1827

Recommendations

• Empirical risk minimization for heavy-tailed losses
• Asymptotic Minimax Parameter Estimation for Nonsymmetric Loss Functions
• Minimum Proper Loss Estimators for Parametric Models
• Minimax estimation of parameter for a class of scale distributions under different loss functions
• On estimation with balanced loss functions
• scientific article; zbMATH DE number 1843526
• scientific article; zbMATH DE number 3854261

zbMATH Keywords

least squareslinear regressionheavy-tailed distributionsunbounded losses

Mathematics Subject Classification ID

Point estimation (62F10) Linear regression; mixed models (62J05) Ridge regression; shrinkage estimators (Lasso) (62J07)

Cited In (54)

• Robust subgaussian estimation with VC-dimension
• Stochastic algorithms with geometric step decay converge linearly on sharp functions
• ARFIS: an adaptive robust model for regression with heavy-tailed distribution
• Exponential concentration for geometric-median-of-means in non-positive curvature spaces
• A shrinkage principle for heavy-tailed data: high-dimensional robust low-rank matrix recovery
• Efficient learning with robust gradient descent
• Robust regression using biased objectives
• On the optimality of averaging in distributed statistical learning
• On the measure of anchored Gaussian simplices, with applications to multivariate medians
• Finite-sample analysis of \(M\)-estimators using self-concordance
• A New Principle for Tuning-Free Huber Regression
• Realizable learning is all you need
• General procedure to provide high-probability guarantees for stochastic saddle point problems
• Sub-Gaussian estimators of the mean of a random vector
• High dimensional generalized linear models for temporal dependent data
• Title not available (Why is that?)
• Solvable integration problems and optimal sample size selection
• Mean estimation with sub-Gaussian rates in polynomial time
• Algorithms of robust stochastic optimization based on mirror descent method
• The geometric median and applications to robust mean estimation
• Finite sample performance of linear least squares estimation
• Near-optimal mean estimators with respect to general norms
• Sub-Gaussian estimators of the mean of a random matrix with heavy-tailed entries
• Convergence rates of least squares regression estimators with heavy-tailed errors
• Distribution-free robust linear regression
• Title not available (Why is that?)
• Title not available (Why is that?)
• Simpler PAC-Bayesian bounds for hostile data
• Random design analysis of ridge regression
• A loss minimization problem
• Robust high-dimensional tuning free multiple testing
• Contextual bandits with continuous actions: smoothing, zooming, and adapting
• Optimal robust mean and location estimation via convex programs with respect to any pseudo-norms
• Robust inference via multiplier bootstrap
• Mean estimation in high dimension
• Mean estimation and regression under heavy-tailed distributions: A survey
• Regularization, sparse recovery, and median-of-means tournaments
• Fast rates for general unbounded loss functions: from ERM to generalized Bayes
• Empirical risk minimization for heavy-tailed losses
• Posterior concentration and fast convergence rates for generalized Bayesian learning
• Finite sample properties of parametric MMD estimation: robustness to misspecification and dependence
• Scale calibration for high-dimensional robust regression
• Minimum Proper Loss Estimators for Parametric Models
• Geometric median and robust estimation in Banach spaces
• Learning without concentration for general loss functions
• Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices
• Distributed statistical estimation and rates of convergence in normal approximation
• Robust supervised learning with coordinate gradient descent
• Robust linear least squares regression
• Optimal influence curves for general loss functions
• User-friendly covariance estimation for heavy-tailed distributions
• Robust and scalable Bayes via a median of subset posterior measures
• Title not available (Why is that?)
• Title not available (Why is that?)

This page was built for publication: Loss minimization and parameter estimation with heavy tails

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2810786)