Research map / Bandits and online learning / Multi-armed bandits
An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits
Julian Katz-Samuels, Lalit Jain, zohar karnin, Kevin G. Jamieson
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 FBPeace instead of uniform sampling | Fixed-budget multivariate testing · Multivariate testing (k=6, d=3) | likelihood of returning the optimal layout: 30% more likely at 10000 samples | Improved |
| Use Peace rather than RAGE as the number of candidate arms increases | Linear bandit identification · Linear bandits (10^3 to 10^6 arms) | sample count: constant vs. linearly in log(|Z|) | Improved |
| Use Peace rather than CLUCB to identify a close second-best matching | Combinatorial bandit identification · Matching | sample complexity as the reward gap h shrinks: roughly |U|/h^2 -> roughly 1/h^2 | Improved |
| Use Peace rather than CLUCB for shortest-path identification | Combinatorial bandit identification · Shortest Path | sample complexity as the reward gap h shrinks | Improved |
| Optimize the experimental design for Gaussian width instead of relying on a union bound over candidate arms | Peace · Transductive linear bandits | sample complexity dependence on the candidate set: avoids an explicit union bound over the number of arms | Improved |
Closest papers by meaning
- Robust Pure Exploration in Linear Bandits with Limited Budget (ICML 2021 · similarity 0.89)
- Minimal Exploration in Structured Stochastic Bandits (NeurIPS 2017 · similarity 0.89)
- Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits (ICLR 2025 · similarity 0.89)
- Bayesian Analysis of Combinatorial Gaussian Process Bandits (ICLR 2025 · similarity 0.87)
- Matroid Semi-Bandits in Sublinear Time (ICML 2024 · similarity 0.87)
- The Batch Complexity of Bandit Pure Exploration (ICML 2025 · 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.
