Research map / Bandits and online learning / Online convex optimization and games
Online Non-Convex Optimization with Imperfect Feedback
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 entropic regularization rather than L2 regularization (ablation) | Dual averaging with unbiased feedback · Online non-convex optimization | static regret: \bigoh(\nRuns^{\frac{\vdim+1}{\vdim+2}}) with L2 regularization; \bigoh(\nRuns^{1/2}) with entropic regularization | Helped |
| Construct smoothed loss models from realized losses and add explicit exploration | Dual averaging with Hedge variant · Online non-convex optimization, bandit feedback | static regret: \bigoh(\nRuns^{\frac{\vdim+2}{\vdim+3}}) | Helped |
| Tune the smoothing radius to balance estimator bias and variance | BDA · Online non-convex optimization, bandit feedback | static regret: \bigoh(\nRuns^{\frac{\vdim+2}{\vdim+3}}) | Helped |
Closest papers by meaning
- Dynamic Regret Reduces to Kernelized Static Regret (NeurIPS 2025 · similarity 0.90)
- A Reduction from Delayed to Immediate Feedback for Online Convex Optimization with Improved Guarantees (NeurIPS 2026 · similarity 0.90)
- Revisiting Projection-Free Online Learning with Time-Varying Constraints (AAAI 2025 · similarity 0.89)
- Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability (ICML 2025 · similarity 0.89)
- Small-loss Adaptive Regret for Online Convex Optimization (ICML 2024 · similarity 0.89)
- Capacity-Constrained Online Convex Optimization with Delayed Feedback (NeurIPS 2026 · similarity 0.89)
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.