Research map / Learning theory and algorithms / Sample complexity
On the Efficient Implementation of High Accuracy Optimality of Profile Maximum Likelihood
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 |
|---|---|---|---|
| Replace direct approximate-PML rounding with weak approximate PML using swap-based matrix rounding | PML-based universal estimation · Symmetric property estimation | sample-optimality accuracy regime: \epsilon \gg n^{-1/4} -> \epsilon \gg n^{-1/3} | Helped |
| Use a weak approximate PML rather than requiring a stronger direct approximation to PML | Efficient PML-based unified estimator · Symmetric property estimation | failure probability bound: \delta^{1-c}\exp(n^{1/3+c}) | Helped |
| Use swap operations before rounding the matrix | Approximate PML algorithm · Profiles with k distinct frequencies and discretization set R | PML objective approximation: \exp(-O(\min(k,|\textbf{R}|)\log n)) | Helped |
Closest papers by meaning
- A General Framework for Symmetric Property Estimation (NeurIPS 2019 · similarity 0.95)
- Instance Based Approximations to Profile Maximum Likelihood (NeurIPS 2020 · similarity 0.93)
- A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions (ICML 2017 · similarity 0.92)
- Instance-Optimality for Private KL Distribution Estimation (NeurIPS 2025 · similarity 0.86)
- Optimal Algorithms for Augmented Testing of Discrete Distributions (NeurIPS 2024 · similarity 0.84)
- Profile Reconstruction from Private Sketches (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.