Research map / Bandits and online learning / Online convex optimization and games
Robust Lipschitz Bandits to Adversarial Corruptions
Yue Kang, Cho-Jui Hsieh, Thomas Chun Man Lee
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 |
|---|---|---|---|
| Use Robust Zooming with a confidence radius containing a corruption-budget term | Zooming · Lipschitz bandits, strong adversary, known C | regret upper bound: O\left( \ln{(T)}^{\frac{1}{d_{z}+2}} T^{\frac{d_{z}+1}{d_{z}+2}} + C^{\frac{1}{d_{z}+1}} T^{\frac{d_{z}}{d_{z}+1}} \righ | Improved |
| Cap the corruption part of Robust Zooming’s confidence radius at 1 (ablation) | Robust Zooming · Strong adversary, known C | regret upper bound | No clear effect |
| Perform RMEL elimination after each round instead of after each epoch (ablation) | RMEL · Weak adversary, unknown C | elimination speed | Improved |
| Use a larger tolerance ratio B between adjacent RMEL layers (ablation) | RMEL · Weak adversary, unknown C | regret upper bound | Hurt |
| Use RMEL or BoB Robust Zooming rather than classic Zooming under Oracle and Garcelon attacks | Lipschitz bandits · Simulated strong-adversary Oracle and Garcelon attacks | cumulative regret | Improved |
| Use RMEL rather than BoB Robust Zooming under the tested attack settings | Lipschitz bandits · Simulated Oracle and Garcelon attacks | cumulative regret | Improved |
Closest papers by meaning
- Stochastic Bandits Robust to Adversarial Attacks (ICLR 2025 · similarity 0.90)
- A Near-optimal, Scalable and Parallelizable Framework for Stochastic Bandits Robust to Adversarial Corruptions and Beyond (NeurIPS 2025 · similarity 0.89)
- Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification (NeurIPS 2024 · similarity 0.88)
- Lipschitz Dueling Bandits over Continuous Action Spaces (NeurIPS 2026 · similarity 0.88)
- Non-Stationary Lipschitz Bandits (NeurIPS 2025 · similarity 0.87)
- Sparsity-Agnostic Linear Bandits with Adaptive Adversaries (NeurIPS 2024 · similarity 0.87)
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.
