Research map / Learning theory and algorithms / Sample complexity
Instance Based Approximations to 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 |
|---|---|---|---|
| Make the PML approximation depend on the number of distinct observed frequencies | ApproximatePML · Profiles with k distinct frequencies | PML approximation factor: \exp(-O(\sqrt{n}\log n)) -> \exp(-O(k\log n)) | Helped |
| Use sparsity in the convex relaxation and a new matrix-rounding algorithm | ApproximatePML · Profiles with k distinct frequencies | PML approximation factor: \exp(-O(\sqrt{n}\log n)) -> \exp(-O(k\log n)) | Helped |
| Implement PseudoPML using the simpler rounding algorithm | Entropy estimation · Entropy estimation, domain size N=10^5 | RMSE | No clear effect |
| Implement PseudoPML using the simpler rounding algorithm | Entropy estimation · Entropy estimation | Runtime | Hurt |
Closest papers by meaning
- On the Efficient Implementation of High Accuracy Optimality of Profile Maximum Likelihood (NeurIPS 2022 · similarity 0.93)
- The Broad Optimality of Profile Maximum Likelihood (NeurIPS 2019 · similarity 0.92)
- A General Framework for Symmetric Property Estimation (NeurIPS 2019 · 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 0.82)
- Direct Fisher Score Estimation for Likelihood Maximization (NeurIPS 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.