Research map / Bandits and online learning / Online convex optimization and games
Online Learning under Adversarial Nonlinear Constraints
Pavel Kolev, Georg Martius, Michael Muehlebach
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 |
|---|---|---|---|
| Replace Online Gradient Descent full projection with CVV-Pro velocity projection using only violated constraints | online constrained learner · Two-player game with shared resources | average runtime per iteration (s): 0.18 -> 0.11 | Improved |
| Replace OGD with CVV-Pro | online constrained learner · Two-player game with shared resources | regret vs 5 sqrt(t) | Improved |
| Run CVV-Pro with random problem instances (n=100, m=10, T=4000) | CVV-Pro · Two-player game, 5 sampled instances | regret, constraint violation, averaged decisions rate | Improved |
Closest papers by meaning
- Revisiting Projection-Free Online Learning with Time-Varying Constraints (AAAI 2025 · similarity 0.90)
- Beyond $\tilde{O}(\sqrt{T})$ Constraint Violation for Online Convex Optimization with Adversarial Constraints (NeurIPS 2025 · similarity 0.90)
- Projection-Free Online Convex Optimization with Time-Varying Constraints (ICML 2024 · similarity 0.89)
- Optimal Algorithms for Online Convex Optimization with Adversarial Constraints (NeurIPS 2024 · similarity 0.89)
- Learning Adversarial MDPs with Stochastic Hard Constraints (ICML 2025 · similarity 0.88)
- Gradient-Variation Online Learning under Generalized Smoothness (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.
