Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Efficient Algorithms for Adversarial Contextual Learning
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 |
|---|---|---|---|
| Add Laplace-perturbed fake-sample augmentation to follow-the-perturbed-leader (contlin) in transductive setting | contextual online combinatorial optimization · transductive full-information | regret bound | Helped |
| Use symmetric Laplace perturbation rather than non-negative (exponential/uniform) perturbation | FTPL error term · full-information regret analysis | dependence of error term on d: sqrt(d) instead of d | Helped |
| Geometric sampling of fake-noise re-invocations to build proxy loss vectors for semi-bandit feedback | contextual semi-bandit algorithm · transductive contextual bandit | regret bound | Helped |
| Time index appended to context to handle switching regret with k switches | contextual linear optimization with switching · transductive switching regret | regret bound | Helped |
| Add predictor Q^t of loss to the oracle call (predictable sequences) | contlin with predictors · path-length / predictor-based regret | regret bound | Helped |
Closest papers by meaning
- First- and Second-Order Bounds for Adversarial Linear Contextual Bandits (NeurIPS 2023 · similarity 0.94)
- An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction (NeurIPS 2025 · similarity 0.93)
- Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits (NeurIPS 2016 · similarity 0.93)
- Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits (NeurIPS 2023 · similarity 0.93)
- Active Context Selection Improves Simple Regret in Contextual Bandits (NeurIPS 2026 · similarity 0.91)
- Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback (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.