Research map / Optimization / Nonconvex and smooth optimization
Variance-based Regularization with Convex Objectives
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 variance-based robust regularization instead of ERM | classification problems · classification problems (datasets unspecified) | out-of-sample test performance | Helped |
| use variance-based robust regularization instead of ERM | robustly regularized estimators · harder, higher-variance instances | performance | Helped |
| use variance-based robust regularization instead of ERM | classification estimators · rare and common classes | class performance | Mixed |
| choose the robust estimator rather than ERM | median estimation on {-1, 0, 1} · constructed discrete median problem | excess risk rate: log n / n vs. 1 / sqrt{n} | Helped |
| use robust regularization rather than ERM | correctly specified linear regression with Gaussian noise · classical linear regression | asymptotic efficiency | No clear effect |
| use robust regularization rather than ERM | general smooth statistical estimation problems · asymptotic estimator distribution | asymptotic bias: sqrt{2 tol} | Hurt |
Closest papers by meaning
- Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization (NeurIPS 2017 · similarity 0.90)
- Stochastic Gradient Methods for Distributionally Robust Optimization with f-divergences (NeurIPS 2016 · similarity 0.89)
- Distributionally Robust Optimization with Bias and Variance Reduction (ICLR 2024 · similarity 0.88)
- Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization (NeurIPS 2024 · similarity 0.87)
- Drago: Primal-Dual Coupled Variance Reduction for Faster Distributionally Robust Optimization (NeurIPS 2024 · similarity 0.87)
- The Bias-Variance Tradeoff in Data-Driven Optimization: A Local Misspecification Perspective (NeurIPS 2025 · similarity 0.87)
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.