Research map / Learning theory and algorithms / Sample complexity
Sequential Algorithms for Testing Closeness of Distributions
Aadil Oufkir, Omar Fawzi, Nicolas Flammarion, Aurélien Garivier
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 a sequential tester instead of a batch tester | closeness testing · small alphabet n << log(1/delta) | sample complexity: reduction by a factor of at least 4 | Improved |
| let the sequential tester stop early when distributions are far (TV >> epsilon) | sequential closeness tester · Monte-Carlo, 100 runs, uniform vs perturbed | stopping time | Improved |
| replace epsilon by max(epsilon, TV(D1,D2)) in the sample complexity | sequential closeness tester · general n >= 2 | sample complexity | Improved |
| use log log(1/d) time-uniform stopping rules instead of the earlier sequential algorithm | sequential closeness tester · epsilon = 0 | sample complexity | Improved |
Closest papers by meaning
- Optimal Algorithms for Augmented Testing of Discrete Distributions (NeurIPS 2024 · similarity 0.88)
- Replicable Distribution Testing (NeurIPS 2025 · similarity 0.86)
- Sequential Kernel Goodness-of-fit Testing (ICML 2024 · similarity 0.85)
- A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers (NeurIPS 2024 · similarity 0.85)
- Differentially Private Equivalence Testing for Continuous Distributions and Applications (NeurIPS 2024 · similarity 0.85)
- Replicable Uniformity Testing (NeurIPS 2024 · similarity 0.84)
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.
