Research map / Bandits and online learning / Multi-armed bandits
Asymptotically Best Causal Effect Identification with Multi-Armed Bandits
Alan Malek, Silvia Chiappa
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 CS-LUCB confidence-sequence best-arm identification instead of uniform sampling of estimators | formula selection (linear model, 9 formulas) · Linear model, M=3 | samples to terminate: needing 34% of uniform samples | Improved |
| use CS-SE successive elimination instead of uniform sampling of estimators | formula selection (linear model, 9 formulas) · Linear model, M=3 | samples to terminate: needing 51% of uniform samples | Improved |
| CS-LUCB and CS-SE vs uniform on nonlinear model with nonparametric (gradient-boosted tree) nuisance estimators | formula selection (nonlinear model, 9 formulas) · Nonlinear model, M=3 | samples to terminate | Improved |
| increase number of formulas from 9 to 65 (M from 3 to 6) | CS-LUCB and CS-SE · Nonlinear model, sample complexity vs number of formulas | samples to terminate | Improved |
| increase number of formulas from 9 to 65 (M from 3 to 6) | uniform sampling baseline · Nonlinear model, sample complexity vs number of formulas | samples to terminate | Hurt |
Closest papers by meaning
- Balancing Performance and Costs in Best Arm Identification (NeurIPS 2025 · similarity 0.90)
- Does 1/2-Tsallis-INF Also Work Well for Best-Arm Identification? (NeurIPS 2026 · similarity 0.89)
- Partial Structure Discovery is Sufficient for No-regret Learning in Causal Bandits (NeurIPS 2024 · similarity 0.89)
- Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits (NeurIPS 2026 · similarity 0.89)
- On the Asymptotic Optimality of Confidence Interval Based Algorithms for Fixed Confidence MABs (AAAI 2025 · similarity 0.88)
- Robustly Improving Bandit Algorithms with Confounded and Selection Biased Offline Data: A Causal Approach (AAAI 2024 · similarity 0.88)
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.
