arXiv (All)
open access
Follow the Perturbed Leader for Linear Bandits: $\sqrt{T}$ Regret over General Convex Sets
We give the first adversarial linear bandit algorithm based on Follow-the-Perturbed-Leader (FTPL) that achieves $\sqrt{T}$ regret over general convex action sets. Our algorithm attains $\widetilde{\mathcal{O}}(d^{5/4}\sqrt{T})$ regret using only linear optimization oracles, and the near-optimal $\wi
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- The Curvature of Regret in Contextual Linear Optimization#1161053
- The Curvature of Regret in Contextual Linear Optimization#1157328
- The Surrogate Is Not the Reward: Post-Surrogate Primary-Outcome Acquisition in Contextual Bandits#1215706
- The Surrogate Is Not the Reward: Post-Surrogate Primary-Outcome Acquisition in Contextual Bandits#1194460
- Sharp Characterization of Bias in Post-Bandit Inference#1052257
Record · ID 1343025
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive