Research map / Bandits and online learning / Online convex optimization and games
Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization
Sijia Chen, Wei-Wei Tu, Peng Zhao, Lijun Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| convexity assumption moved from individual functions to expected functions in optimistic OMD | optimistic OMD on SEA convex smooth · SEA convex smooth | expected static regret | No clear effect |
| refined log-variation analysis for strongly convex case | optimistic OMD strongly convex smooth · SEA strongly convex smooth | expected static regret | Improved |
| two-layer ensemble with correction terms for dynamic regret | optimistic OMD convex smooth · SEA convex smooth dynamic regret | expected dynamic regret | Improved |
| implicit update in optimistic step (non-smooth functions) | optimistic OMD convex non-smooth · SEA convex non-smooth static regret | expected static regret | Mixed |
| alternative optimism design using gradient at averaged decision (Sachs et al. style) (ablation) | two-layer dynamic regret algorithm · SEA smooth dynamic regret | expected dynamic regret | Hurt |
Closest papers by meaning
- Online Composite Optimization Between Stochastic and Adversarial Environments (NeurIPS 2024 · similarity 0.95)
- Parameter-free Algorithms for the Stochastically Extended Adversarial Model (NeurIPS 2025 · similarity 0.92)
- Optimal Algorithms for Online Convex Optimization with Adversarial Constraints (NeurIPS 2024 · similarity 0.89)
- Stochastic Shortest Path with Sparse Adversarial Costs (NeurIPS 2025 · similarity 0.89)
- Gradient-Variation Online Learning under Generalized Smoothness (NeurIPS 2024 · similarity 0.88)
- A Simple and Optimal Approach for Universal Online Learning with Gradient Variations (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.
