Research map / Bandits and online learning / Online convex optimization and games
On Online Optimization: Dynamic Regret Analysis of Strongly Convex and Smooth Problems
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 positive-definite preconditioning with one gradient query per round | OPGD · Unconstrained strongly convex and smooth online optimization | dynamic regret upper bound: O(C^*_{2,T}) | Helped |
| Use accurate predictions of the gradient and Hessian | OON · Unconstrained strongly convex and smooth online optimization | dynamic regret upper bound: O(D'_T+C^*_{4,T}) | Helped |
| Use stale previous-round gradient and Hessian information instead of accurate predictions (ablation) | OON · Unconstrained strongly convex and smooth online optimization | dynamic regret upper bound: O(C^*_{2,T}) | Mixed |
| Use multiple gradient descents per round | OMGD · Unconstrained strongly convex and smooth online optimization | dynamic regret upper bound: O(min {V_T, C^*_{2,T}}) | Helped |
| Use the identity preconditioner, yielding ordinary OGD (ablation) | OPGD · Unconstrained strongly convex and smooth online optimization | dynamic regret upper bound: O(C_{2,T}^*) | No clear effect |
Closest papers by meaning
- Dynamic Regret of Convex and Smooth Functions (NeurIPS 2020 · similarity 0.94)
- Dynamic Regret Reduces to Kernelized Static Regret (NeurIPS 2025 · similarity 0.92)
- Non-stationary Online Convex Optimization with Arbitrary Delays (ICML 2024 · similarity 0.91)
- An Equivalence Between Static and Dynamic Regret Minimization (NeurIPS 2024 · similarity 0.91)
- Small-loss Adaptive Regret for Online Convex Optimization (ICML 2024 · similarity 0.91)
- Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness (NeurIPS 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.