Research map / Bandits and online learning / Online convex optimization and games
Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds
Taira Tsuchiya, Shinji Ito, Junya Honda
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 sparsity-aware tuned bound with s-agnostic SPA learning rate | FTRL with SPA learning rate · MAB losses in [0,1], adversarial | regret bound | Improved |
| Use SPA learning rate for losses in [-1,1] instead of prior bound 10 sqrt(L2 log k) + 20 k log T | FTRL with SPA learning rate · MAB losses in [-1,1], adversarial | regret bound constants: 10 -> 4, 20 k log T -> 2 k log T | Improved |
| Add best-of-both-worlds guarantee with sparsity-dependent bound | SPA FTRL · MAB, stochastic regime | regret bound | Improved |
| Make partial monitoring bound game-dependent and BOBW simultaneously | SPA FTRL · Non-degenerate local PM games | regret bound | Improved |
Closest papers by meaning
- A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds (NeurIPS 2024 · similarity 0.91)
- Follow-the-Perturbed-Leader Nearly Achieves Best-of-Both-Worlds for the m-Set Semi-Bandit Problems (NeurIPS 2025 · similarity 0.89)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.89)
- Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems (NeurIPS 2025 · similarity 0.89)
- Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals (ICML 2024 · similarity 0.89)
- Sparsity-Agnostic Linear Bandits with Adaptive Adversaries (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.
