Research map / Learning theory and algorithms / Sample complexity
A General Framework for Symmetric Property 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 |
|---|---|---|---|
| Restrict the PML subroutine to frequencies ≤ 18 and use empirical estimation for the rest | Entropy estimation on Zipf(1) · Zipf(1), 10^3 to 5*10^6 samples | speedup over raw PML: 0.824, 1.205, 1.669, 3.561, 4.852, 9.552, 13.337, 12.196 | Mixed |
| Use empirical estimation for frequencies above 18, reserving PML for frequencies ≤ 18 | Entropy estimation on Zipf(1) · Zipf(1), 10^3 to 5*10^6 samples | empirical-estimate fraction: 0.184, 0.317, 0.372, 0.505, 0.562, 0.695, 0.752, 0.886 | Helped |
| Use pseudo PML with empirical estimation on the easy-frequency region instead of applying raw PML throughout | Entropy estimation · Distributions with domain size N=10^5 | entropy estimation error | No clear effect |
Closest papers by meaning
- On the Efficient Implementation of High Accuracy Optimality of Profile Maximum Likelihood (NeurIPS 2022 · similarity 0.95)
- A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions (ICML 2017 · similarity 0.92)
- Instance Based Approximations to Profile Maximum Likelihood (NeurIPS 2020 · similarity 0.91)
- Instance-Optimality for Private KL Distribution Estimation (NeurIPS 2025 · similarity 0.84)
- Optimal Algorithms for Augmented Testing of Discrete Distributions (NeurIPS 2024 · similarity 0.84)
- Dimension-free Private Mean Estimation for Anisotropic Distributions (NeurIPS 2024 · 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.