Research map / Bandits and online learning / Online convex optimization and games
Adaptive Online Learning in Dynamic Environments
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 |
|---|---|---|---|
| Adapt the step size to unknown comparator path-length using multiple OGD experts and expert tracking | Online gradient descent for general dynamic regret · General dynamic regret (arbitrary comparator sequence) | dynamic regret upper bound: O\left(\sqrt{T} (1+P_T)\right) -> O\left(\sqrt{T(1+P_T)} \right) | Helped |
| Use a surrogate loss and shared gradient evaluation for expert updates | Ader · General dynamic regret (arbitrary comparator sequence) | gradient evaluations per round: O(\log T) -> 1 | Helped |
| Use surrogate loss and shared gradient evaluation for expert updates | Ader · General dynamic regret (arbitrary comparator sequence) | dynamic regret upper bound | No clear effect |
| Incorporate contraction dynamical models and measure comparator variation by deviation from those models | Ader · Dynamic regret with dynamical models | dynamic regret upper bound: O(\sqrt{T} (1+P_T')) -> O\left(\sqrt{T(1+P_T')} \right) | Helped |
Closest papers by meaning
- Dynamic Regret in Online Convex Optimization with Indicator Switching Costs (NeurIPS 2026 · similarity 0.92)
- Dynamic Regret Reduces to Kernelized Static Regret (NeurIPS 2025 · similarity 0.91)
- An Equivalence Between Static and Dynamic Regret Minimization (NeurIPS 2024 · similarity 0.91)
- Non-stationary Online Convex Optimization with Arbitrary Delays (ICML 2024 · similarity 0.90)
- Online Non-convex Learning in Dynamic Environments (NeurIPS 2024 · similarity 0.90)
- On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning (ICML 2025 · 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.