Research map / Optimization / Nonconvex and smooth optimization
Stochastic Gradient Methods for Distributionally Robust Optimization with f-divergences
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use bandit mirror descent with O(log n) BST-based updates instead of full-gradient updates over all n terms | robust ERM with chi-square f-divergence · Reuters RCV1 large-scale | optimality of robust objective vs CPU time | Helped |
| Gradient descent on the robust objective used instead of bandit mirror descent | robust ERM with chi-square f-divergence · Reuters RCV1 large-scale | optimality of robust objective vs CPU time | Mixed |
| Robust DRO objective (chi-square, rho=chi2_{1,.9}) used instead of plain ERM | logistic/hinge classification · Adult, Reuters RCV1 | upper confidence bound on test risk | No clear effect |
Closest papers by meaning
- Distributionally Robust Optimization with Bias and Variance Reduction (ICLR 2024 · similarity 0.92)
- Distributionally Robust Performative Optimization (NeurIPS 2025 · similarity 0.90)
- Large-Scale Non-convex Stochastic Constrained Distributionally Robust Optimization (AAAI 2024 · similarity 0.89)
- Generalization Analysis of Biased Stochastic Gradient Methods for Minimax Problems (NeurIPS 2026 · similarity 0.89)
- Drago: Primal-Dual Coupled Variance Reduction for Faster Distributionally Robust Optimization (NeurIPS 2024 · similarity 0.88)
- Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.