Suboptimality of constrained least squares and improvements via non-linear predictors

Tomas Vaškevičius, Nikita Zhivotovskiy

Publication date: 19 December 2022

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2009.09304

zbMATH Keywords

empirical processes ridge regression constrained least squares average stability Vovk-Azoury-Warmuth forecaster

Mathematics Subject Classification ID

Linear inference, regression (62Jxx) Artificial intelligence (68Txx) Nonparametric inference (62Gxx)

Related Items (1)

Suboptimality of constrained least squares and improvements via non-linear predictors

Cites Work

Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Performance of empirical risk minimization in linear aggregation
The lower tail of random quadratic forms with applications to ordinary least squares
Random design analysis of ridge regression
A new perspective on least squares under convex constraint
Empirical entropy, minimax regret and minimax risk
Probability in Banach spaces. Isoperimetry and processes
Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
Sums of random Hermitian matrices and an inequality by Rudelson
Robust linear least squares regression
Learning by mirror averaging
Logarithmic regret algorithms for online convex optimization
Random vectors in the isotropic position
Rates of convergence for minimum contrast estimators
Relative expected instantaneous loss bounds
On optimality of empirical risk minimization in linear aggregation
Sharp oracle inequalities for least squares estimators in shape restricted regression
Minimax estimation via wavelet shrinkage
A distribution-free theory of nonparametric regression
Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices
Suboptimality of constrained least squares and improvements via non-linear predictors
Distribution-free robust linear regression
Robust statistical learning with Lipschitz and convex loss functions
Uniform Hanson-Wright type concentration inequalities for unbounded entries via the entropy method
Robust covariance estimation under \(L_4\)-\(L_2\) norm equivalence
Risk minimization by median-of-means tournaments
Isotonic regression in general dimensions
Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
Fast learning rates in statistical inference through aggregation
Empirical risk minimization is optimal for the convex aggregation problem
Model selection via testing: an alternative to (penalized) maximum likelihood estimators.
Empirical minimization
On risk bounds in isotonic and other shape restricted regression problems
Local Rademacher complexities
Learning without Concentration
How Many Variables Should be Entered in a Regression Equation?
High-Dimensional Statistics
High-Dimensional Probability
Competitive On-line Statistics
Extending the scope of the small-ball method
Learning Theory and Kernel Machines
Prediction, Learning, and Games
Understanding Machine Learning
An Introduction to Matrix Concentration Inequalities
Relative loss bounds for on-line density estimation with the exponential family of distributions

This page was built for publication: Suboptimality of constrained least squares and improvements via non-linear predictors