Research map / Learning theory and algorithms / Sample complexity
Instance Dependent Testing of Samplers Using Interval Conditioning
Rishiraj Bhattacharyya, Sourav Chakraborty, Yash Pote, Uddalok Sarkar, Sayantan Sen
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 interval-conditioning tester Lachesis instead of CubeProbe | CubeProbe · Binomial samplers, n 1,000 to 600,000 | number of oracle queries / runtime: average speedup over 1000x | Improved |
| run Lachesis on buggy samplers with perturbed constants | Lachesis · Binomial and Poisson samplers (implementations 2-6) | detection of incorrect samplers | Improved |
| benign changes to rejection sampling parameters in Poisson samplers | Lachesis · Poisson implementations 5 and 6 | acceptance of correct samplers | Improved |
Closest papers by meaning
- Testing Self-Reducible Samplers (AAAI 2024 · similarity 0.87)
- Optimal Algorithms for Augmented Testing of Discrete Distributions (NeurIPS 2024 · similarity 0.87)
- A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers (NeurIPS 2024 · similarity 0.84)
- Replicable Distribution Testing (NeurIPS 2025 · similarity 0.84)
- Replicable Uniformity Testing (NeurIPS 2024 · similarity 0.82)
- Sample-Adaptivity Tradeoff in On-Demand Sampling (NeurIPS 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.
