Research map / Learning theory and algorithms / Sample complexity
Distribution Compression in Near-Linear Time
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Apply Compress++ to KT | KT · 65,000 points, 10 dimensions | runtime: 20m -> 1.5m | Helped |
| Apply Compress++ to KT | KT · 250,000 points, 100 dimensions | runtime: more than a day -> less than an hour; 32× speed-up | Helped |
| Apply Compress++ to KT | KT · Gaussian targets and MCMC posterior targets | MMD | No clear effect |
| Apply Compress++ to kernel herding | Herd · 250,000 points, 100 dimensions | runtime: more than 11 hours -> 14 minutes; 45× speed-ups | Helped |
| Apply Compress++ to kernel herding | Herd · Gaussian targets, lower-dimensional problems | MMD | Helped |
| Apply Compress++ to kernel herding | Herd · Gaussian targets | MMD | No clear effect |
| Use Compress++ with a quadratic-time thinning algorithm | KT and kernel herding · Distribution compression | runtime: O(n^2) -> O(n log^3 n) | Helped |
Closest papers by meaning
- Debiased Distribution Compression (ICML 2024 · similarity 0.89)
- Supervised Kernel Thinning (NeurIPS 2024 · similarity 0.86)
- Low-Rank Thinning (ICML 2025 · similarity 0.86)
- Conditional Distribution Compression via the Kernel Conditional Mean Embedding (NeurIPS 2025 · similarity 0.83)
- Faster Sampling via Stochastic Gradient Proximal Sampler (ICML 2024 · similarity 0.82)
- Faster Diffusion Sampling with Randomized Midpoints: Sequential and Parallel (ICLR 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.