Research map / Learning theory and algorithms / Sample complexity
Data Structures for Density Estimation
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 |
|---|---|---|---|
| Use fast tournament (reduced sample sizes in lower tournament levels) instead of base knockout tournament | knockout tournament for hypothesis selection · Half-uniform synthetic data, 60 samples | operations needed for accuracy above 80%: more than 2.4x fewer operations | Helped |
| Use fast tournament instead of base tournament | knockout tournament · Networking CAIDA data | number of Scheffe operations: 5x fewer (nAllPairs=0); 2.4x fewer (nAllPairs=5) | Helped |
| Use fast tournament instead of base tournament | knockout tournament · Networking CAIDA data | TV distance of returned distribution | No clear effect |
| Increase all-pairs comparison at end of tournament (nAllPairs) (ablation) | both tournaments · Synthetic and networking experiments | accuracy | No clear effect |
| Reduce number of samples in earlier tournament rounds (smaller fastConst) (ablation) | fast tournament · Half-uniform synthetic data | accuracy | No clear effect |
| Increase total number of samples (ablation) | both tournaments · Half-uniform synthetic data | accuracy: accuracy rises from 13% at 20 samples to 98% at 60 samples | Helped |
Closest papers by meaning
- Statistical-Computational Trade-offs for Density Estimation (NeurIPS 2024 · similarity 0.94)
- Breaking the curse of dimensionality in structured density estimation (NeurIPS 2024 · similarity 0.86)
- Density Ratio Estimation with Conditional Probability Paths (ICML 2025 · similarity 0.85)
- Optimal Hypothesis Selection in (Almost) Linear Time (NeurIPS 2024 · similarity 0.84)
- Simple and Optimal Sublinear Algorithms for Mean Estimation (NeurIPS 2025 · similarity 0.83)
- Sobolev Space Regularised Pre Density Models (ICML 2024 · 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.