Research map / Bandits and online learning / Online convex optimization and games
Optimal regret algorithm for Pseudo-1d Bandit Convex Optimization
Aadirupa Saha, Nagarajan Natarajan, Praneeth Netrapalli, Prateek Jain
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 |
|---|---|---|---|
| Exploit pseudo-1d structure with a one-dimensional kernelized exponential-weights scheme | PBCO · Pseudo-1d Bandit Convex Optimization, d = O(\sqrt{T}) | regret: O\Big( C\sqrt{dT \log (L'T)} \Big) | Improved |
| Use modified OGD that estimates only the unknown scalar loss derivative | PBCO · Pseudo-1d Bandit Convex Optimization, larger d | regret: 2\sqrt{3WLDC} T^{3/4} | Improved |
| Combine the two dimension-dependent regimes: kernelized exponential weights for smaller d and modified OGD for larger d | OptPBCO · Pseudo-1d Bandit Convex Optimization (adversarial) | regret: 2\sqrt 2 \min \bigg(C\sqrt{dT\log(L'T)}, \sqrt{WLDC}T^{3/4}\bigg) | Improved |
Closest papers by meaning
- Improved Regret for Bandit Convex Optimization with Delayed Feedback (NeurIPS 2024 · similarity 0.92)
- Online Nonsubmodular Optimization with Delayed Feedback in the Bandit Setting (AAAI 2025 · similarity 0.91)
- Dynamic Regret Reduces to Kernelized Static Regret (NeurIPS 2025 · similarity 0.91)
- Non-stationary Bandit Convex Optimization: A Comprehensive Study (NeurIPS 2025 · similarity 0.91)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.90)
- A Reduction from Delayed to Immediate Feedback for Online Convex Optimization with Improved Guarantees (NeurIPS 2026 · 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.
