Robust SGLD algorithm for solving non-convex distributionally robust optimisation problems

DOI10.1007/S00245-026-10519-8MaRDI QIDQ7405673zbMATH OpenFDO

Authors Ariel Neufeld, Matthew Cheng En Ng, Ying Zhang

Publication date 2026

Published in Applied Mathematics and Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S00245-026-10519-8

zbMATH Keywords

algorithms for stochastic optimisationdata-driven optimisationdistributionally robust optimisation (DRO)expected excess risknonlinear regression involving neural networksstochastic gradient Langevin dynamics (SGLD)

Mathematics Subject Classification ID

Calculus of variations and optimal control; optimization (49-XX)

Cites work

• A robust learning approach for regression models based on distributionally robust optimization
• An adaptively weighted stochastic gradient MCMC algorithm for Monte Carlo simulation and global optimization
• Analysis of Langevin Monte Carlo via convex optimization
• Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
• Data-driven risk-averse stochastic optimization with Wasserstein metric
• Distributionally Robust Linear and Discrete Optimization with Marginals
• Distributionally robust optimization under moment uncertainty with application to data-driven problems
• Distributionally robust portfolio maximization and marginal utility pricing in one period financial markets
• Distributionally Robust Stochastic Optimization with Wasserstein Distance
• Markov decision processes under model uncertainty
• Non-asymptotic estimates for TUSLA algorithm for non-convex learning with applications to neural networks with ReLU activation function
• Nonasymptotic estimates for stochastic gradient Langevin dynamics under local conditions in nonconvex optimization
• On stationary-point hitting time and ergodicity of stochastic gradient Langevin dynamics
• On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case
• On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case
• Quantifying distributional model risk via optimal transport
• Risk, ambiguity and the Savage axioms
• Robust risk aggregation with neural networks
• Sensitivity analysis of Wasserstein distributionally robust optimization problems
• Taming Neural Networks with TUSLA: Nonconvex Learning via Adaptive Stochastic Gradient Langevin Algorithms
• User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
• Wasserstein distributionally robust optimization and variation regularization

This page was built for publication: Robust SGLD algorithm for solving non-convex distributionally robust optimisation problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7405673)