Research map / Bandits and online learning / Online convex optimization and games
Dynamic Regret of Strongly Adaptive Methods
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 |
|---|---|---|---|
| Use a strongly adaptive method and bound dynamic regret using functional variation | Online convex functions · Online convex functions | dynamic regret: O \left( \max\left\{ \sqrt{T \log T} , T^{2/3} V_T^{1/3} \log^{1/3} T \right\} \right) | Helped |
| Use IFLH with online Newton step | Online exp-concave functions · Online exp-concave functions | dynamic regret: O \left(d \cdot \max\left\{ \log T, \sqrt{T V_T \log T} \right\} \right) | Helped |
| Use IFLH with online gradient descent instead of the dimension-dependent exp-concave route | Online strongly convex functions · Online strongly convex functions | dynamic regret: O \left( \max\left\{ \log T, \sqrt{T V_T \log T} \right\} \right) | Helped |
| Set the IFLH base parameter K to 2 (ablation) | IFLH with online Newton step · Online exp-concave functions | strongly adaptive regret: O(d \log^2 T) | Hurt |
| Set the IFLH base parameter K to \lceil T^{1/\gamma}\rceil (ablation) | IFLH with online Newton step · Online exp-concave functions | strongly adaptive regret: O(\gamma d \log T) | Helped |
| Set the IFLH base parameter K to T (ablation) | IFLH with online Newton step · Online exp-concave functions | strongly adaptive regret: O(d \log T) | Helped |
Closest papers by meaning
- Small-loss Adaptive Regret for Online Convex Optimization (ICML 2024 · similarity 0.92)
- Dynamic Regret Reduces to Kernelized Static Regret (NeurIPS 2025 · similarity 0.90)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.90)
- Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability (ICML 2025 · similarity 0.89)
- An Equivalence Between Static and Dynamic Regret Minimization (NeurIPS 2024 · similarity 0.89)
- A Simple and Optimal Approach for Universal Online Learning with Gradient Variations (NeurIPS 2024 · 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.