Diametrical risk minimization: theory and computations

DOI10.1007/s10994-021-06036-0zbMath1518.91315arXiv1910.10844OpenAlexW3197941240MaRDI QIDQ6134352

Matthew D. Norton, Johannes O. Royset

Publication date: 22 August 2023

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1910.10844

zbMATH Keywords

generalization errorempirical risk minimizationsolution stability

Mathematics Subject Classification ID

Statistical methods; risk measures (91G70) Analysis of algorithms (68W40)

Cites Work

• Unnamed Item
• Characterization of the equivalence of robustification and regularization in linear and matrix regression
• Robust optimization using computer experiments
• Applications of convex optimization in signal processing and digital communication
• Robust sample average approximation
• On robust solutions to linear least squares problems affected by data uncertainty and implementation errors with application to stochastic signal modeling
• Regularisation of neural networks by enforcing Lipschitz continuity
• Sample average approximation with sparsity-inducing penalty for high-dimensional stochastic programming
• On sample size control in sample average approximations for solving smooth stochastic programs
• Robust Convex Optimization
• Concentration Inequalities
• Quantitative Stability Analysis for Distributionally Robust Optimization with Moment Constraints
• Optimal Budget Allocation for Sample Average Approximation
• Fabrication-Adaptive Optimization with an Application to Photonic Crystal Design
• Distributionally Robust Convex Optimization
• Flat Minima
• Lipschitz Behavior of the Robust Regularization
• Lectures on Stochastic Programming
• Variational Analysis
• Multivariate Nonnegative Quadratic Mappings
• 10.1162/153244302760200704
• Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach
• An Optimization Primer
• Variational Theory for Optimization under Stochastic Ambiguity
• Entropy-SGD: biasing gradient descent into wide valleys
• Sample average approximation with heavier tails. I: Non-asymptotic bounds with weak assumptions and stochastic constraints

This page was built for publication: Diametrical risk minimization: theory and computations