Research map / Bandits and online learning / Online convex optimization and games
Improved Dynamic Regret for Non-degenerate Functions
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 |
|---|---|---|---|
| Apply multiple gradient steps per round instead of one | Online gradient descent on strongly convex and smooth functions · Strongly convex and smooth functions | dynamic regret upper bound: O(\P_T^*) to O \left( \min\left(\P_T^*, \SN_T^*\right) \right) | Helped |
| Apply multiple gradient steps per round | Online gradient descent on semi-strongly convex and smooth functions · Semi-strongly convex and smooth functions | dynamic regret upper bound: O(\P_T^*) to O(\min( \P_T^*, \SN_T^*)) | Helped |
| Use multiple damped Newton updates per round, querying gradients and Hessians | Online learning with self-concordant functions · Self-concordant functions | dynamic regret upper bound: O(\min(\P_T^*, \SN_T^* )) | Helped |
| Increase the number of gradient accesses to K = \infty (ablation) | OMGD on strongly convex and smooth functions · Strongly convex and smooth functions | dynamic regret upper bound: K = \infty | No clear effect |
| Use multiple gradient steps to obtain an O(\SN_T^*) bound | Online learning with strongly convex and smooth functions · Strongly convex and smooth functions | dynamic regret lower bound: \Omega(\SN_T^*) | No clear effect |
Closest papers by meaning
- Dynamic Regret Reduces to Kernelized Static Regret (NeurIPS 2025 · similarity 0.93)
- An Equivalence Between Static and Dynamic Regret Minimization (NeurIPS 2024 · similarity 0.92)
- Dynamic Regret in Online Convex Optimization with Indicator Switching Costs (NeurIPS 2026 · similarity 0.91)
- Small-loss Adaptive Regret for Online Convex Optimization (ICML 2024 · similarity 0.91)
- Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability (ICML 2025 · similarity 0.90)
- On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning (ICML 2025 · similarity 0.90)
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.