Variance-based regularization with convex objectives

zbMath1489.62193arXiv1610.02581MaRDI QIDQ5381122

Hongseok Namkoong, John C. Duchi

Publication date: 7 June 2019

Full work available at URL: https://arxiv.org/abs/1610.02581

zbMATH Keywords

robust optimizationempirical likelihoodvariance regularization

Mathematics Subject Classification ID

Asymptotic distribution theory in statistics (62E20) Nonparametric estimation (62G05) General nonlinear regression (62J02)

Related Items (14)

Learning models with uniform performance via distributionally robust optimization ⋮ Weakly-convex–concave min–max optimization: provable algorithms and applications in machine learning ⋮ Robust and distributionally robust optimization models for linear support vector machine ⋮ Robust Simulation with Likelihood-Ratio Constrained Input Uncertainty ⋮ Learning with risks based on M-location ⋮ Unnamed Item ⋮ A survey of learning criteria going beyond the usual risk ⋮ General procedure to provide high-probability guarantees for stochastic saddle point problems ⋮ Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach ⋮ Conditional variance penalties and domain shift robustness ⋮ Variance Regularization in Sequential Bayesian Optimization ⋮ Distributionally robust optimization. A review on theory and applications ⋮ Distributionally robust bottleneck combinatorial problems: uncertainty quantification and robust decision making ⋮ Toward theoretical understandings of robust Markov decision processes: sample complexity and asymptotics

Uses Software

• UCI-ml
• RCV1

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Statistics for high-dimensional data. Methods, theory and applications.
• Covering numbers of Gaussian reproducing kernel Hilbert spaces
• Empirical likelihood ratio confidence regions
• A result of Vapnik with applications
• Smooth discrimination analysis
• A Bennett concentration inequality and its application to suprema of empirical processes
• Optimal aggregation of classifiers in statistical learning.
• Weak convergence and empirical processes. With applications to statistics
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Local Rademacher complexities
• Learning without Concentration
• Theory of Classification: a Survey of Some Recent Advances
• Oracle-Based Robust Optimization via Online Learning
• Capacity of reproducing kernel spaces in learning theory
• Lectures on Stochastic Programming
• Uniform Central Limit Theorems
• 10.1162/1532443041424337
• 10.1162/153244303321897690
• Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach
• Regularization and Variable Selection Via the Elastic Net
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Convexity, Classification, and Risk Bounds
• Introduction to nonparametric estimation
• Smoothing spline ANOVA models

This page was built for publication: Variance-based regularization with convex objectives