Distribution-free robust linear regression
From MaRDI portal
Publication:2113267
DOI10.4171/MSL/27zbMath1493.62429arXiv2102.12919OpenAlexW4205966363MaRDI QIDQ2113267
Nikita Zhivotovskiy, Jaouad Mourtada, Tomas Vaškevičius
Publication date: 11 March 2022
Published in: Mathematical Statistics and Learning (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2102.12919
least squaresrobust estimationimproper learningmedian-of-means tournamentsrandom design linear regression
Related Items
Nonexact oracle inequalities, \(r\)-learnability, and fast rates ⋮ An elementary analysis of ridge regression with random design ⋮ Suboptimality of constrained least squares and improvements via non-linear predictors
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Geometric median and robust estimation in Banach spaces
- Performance of empirical risk minimization in linear aggregation
- Nonparametric stochastic approximation with large step-sizes
- The lower tail of random quadratic forms with applications to ordinary least squares
- Quantitative error estimates for a least-squares Monte Carlo algorithm for American option pricing
- On the stability and accuracy of least squares approximations
- Sub-Gaussian mean estimators
- Adaptive importance sampling in least-squares Monte Carlo algorithms for backward stochastic differential equations
- Empirical entropy, minimax regret and minimax risk
- Robust linear least squares regression
- Aggregation via empirical risk minimization
- Empirical risk minimization for heavy-tailed losses
- Learning by mirror averaging
- Conditions d'intégrabilité pour les multiplicateurs dans le TLC banachique. (Integrability conditions for multiplicators in the central limit theorem in Banach spaces)
- Random generation of combinatorial structures from a uniform distribution
- The space complexity of approximating the frequency moments
- Predicting \(\{ 0,1\}\)-functions on randomly drawn points
- On the strong universal consistency of a series type regression estimate
- Combining different procedures for adaptive regression
- Relative expected instantaneous loss bounds
- On optimality of empirical risk minimization in linear aggregation
- Sub-Gaussian estimators of the mean of a random vector
- Convergence of the Robbins-Monro method for linear problems in a Banach space
- Mixing strategies for density estimation.
- Weak convergence and empirical processes. With applications to statistics
- Challenging the empirical mean and empirical variance: a deviation study
- Robust \(k\)-means clustering for distributions with two moments
- Robust statistical learning with Lipschitz and convex loss functions
- Robust machine learning by median-of-means: theory and practice
- Robust covariance estimation under \(L_4\)-\(L_2\) norm equivalence
- Risk minimization by median-of-means tournaments
- Regression function estimation on non compact support in an heteroscesdastic model
- Convergence rates of least squares regression estimators with heavy-tailed errors
- Mean estimation and regression under heavy-tailed distributions: A survey
- Near-optimal mean estimators with respect to general norms
- On aggregation for heavy-tailed classes
- Optimal rates for the regularized least-squares algorithm
- Fast learning rates in statistical inference through aggregation
- Local Rademacher complexities
- Robust multivariate mean estimation: the optimality of trimmed mean
- Learning without Concentration
- How Many Variables Should be Entered in a Regression Equation?
- A theory of the learnable
- Improving the sample complexity using global data
- Competitive On-line Statistics
- Learning Bounded Subsets of Lₚ
- Extending the scope of the small-ball method
- An Unrestricted Learning Procedure
- Learning Theory and Kernel Machines
- Robust Statistics
- Relative loss bounds for on-line density estimation with the exponential family of distributions
This page was built for publication: Distribution-free robust linear regression