Research map / Learning theory and algorithms / Sample complexity
Greedy Poisson Rejection Sampling
Gergely Flamich
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 binary search variant of GPRS instead of A* coding on unimodal 1D problems | GPRS channel simulation · 1D toy channel simulation problems | expected runtime and codelength | Improved |
| summarize binary-search GPRS performance by mean versus median | binary search GPRS · 1D toy problems | runtime and codelength | No clear effect |
| compare empirical codelength with the proved upper bound | GPRS codelength bound · 1D toy problems | codelength | Mixed |
| use binary search GPRS whose runtime scales with KL(Q||P) instead of D_inf(Q||P) | GPRS · problems with finite KL but large or infinite D_inf | runtime | Improved |
Closest papers by meaning
- Channel Simulation and Distributed Compression with Ensemble Rejection Sampling (NeurIPS 2025 · similarity 0.89)
- Universal Sample Coding (NeurIPS 2024 · similarity 0.87)
- Progressive Compression with Universally Quantized Diffusion Models (ICLR 2025 · similarity 0.84)
- Fast Channel Simulation via Error-Correcting Codes (NeurIPS 2024 · similarity 0.84)
- List-Level Distribution Coupling with Applications to Speculative Decoding and Lossy Compression (NeurIPS 2025 · similarity 0.83)
- Jump Your Steps: Optimizing Sampling Schedule of Discrete Diffusion Models (ICLR 2025 · similarity 0.83)
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.
