Research map / Bandits and online learning / Online convex optimization and games
Adaptive Algorithms for Online Convex Optimization with Long-term Constraints
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 |
|---|---|---|---|
| Adaptive step sizes with trade-off beta tuned to 2/3 (vs. beta=1/2) | A-OGD for OCO with long-term constraints · theory | regret exponents (loss, constraint) | Mixed |
| Strongly convex instead of convex losses in A-OGD (ablation) | A-OGD on doubly-stochastic matrix experiment · doubly-stochastic matrices, T=1000 | cumulative regret on loss and constraint | No clear effect |
| Adaptive A-OGD vs. Convex OGD step sizes on elastic-net sparse classification | A-OGD · sparse online binary classification (ijcnn1, covtype) | cumulative regret on loss | Helped |
| Adding a penalty-free no-violation extension with gamma = c1 T^{-beta/2} tightening | A-OGD with extra gradient condition · theory (Corollary 1) | constraint violation | Helped |
Closest papers by meaning
- Gradient-Variation Bound for Online Convex Optimization with Constraints (AAAI 2023 · similarity 0.94)
- Small-loss Adaptive Regret for Online Convex Optimization (ICML 2024 · similarity 0.92)
- Optimal Algorithms for Online Convex Optimization with Adversarial Constraints (NeurIPS 2024 · similarity 0.92)
- Revisiting Projection-Free Online Learning with Time-Varying Constraints (AAAI 2025 · similarity 0.92)
- Constrained Online Convex Optimization with Polyak Feasibility Steps (ICML 2025 · similarity 0.91)
- Exploiting Curvature in Online Convex Optimization with Delayed Feedback (ICML 2025 · similarity 0.91)
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.