Research map / Bandits and online learning / Multi-armed bandits
Adaptive Data Depth via Multi-Armed Bandits
Tavor Baharav, Tze Leung Lai
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 adaptive bandit-based depth computation instead of brute force | simplicial median computation · isotropic Gaussian, d=2 | runtime scaling exponent: 3.4 -> 1.5 | Improved |
| use adaptive bandit-based depth computation instead of Rousseeuw and Ruts | simplicial median computation · isotropic Gaussian, d=2 | runtime scaling exponent: 2.0 -> 1.5 | Improved |
| use Bernstein-type variance-adaptive confidence intervals instead of Hoeffding (ablation) | adaptive simplicial median · Bernoulli arms, theory | sample complexity | No clear effect |
| use tighter confidence intervals with t_r = ceil(.2 x 2^-r log(4nr^2/delta)) | adaptive simplicial median · simulations d=2 | correctness | No clear effect |
| increase inverse squared gap of a point | adaptive simplicial median · n=20,000 | number of simplices sampled: R^2 = .98 | Hurt |
Closest papers by meaning
- Sparse One-Grab Sampling with Probabilistic Guarantees (TPAMI 2018 · similarity 0.85)
- Geometric Median (GM) Matching for Robust k-Subset Selection from Noisy Data (ICML 2025 · similarity 0.84)
- The Adaptive Complexity of Minimizing Relative Fisher Information (NeurIPS 2025 · similarity 0.83)
- Approximating Metric Magnitude of Point Sets (AAAI 2025 · similarity 0.83)
- Efficient Adaptive Data Analysis over Dense Data Distributions (NeurIPS 2026 · similarity 0.83)
- Learning Distances from Data with Normalizing Flows and Score Matching (ICML 2025 · similarity 0.82)
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.
