Research map / Learning theory and algorithms / Sample complexity
TURF: Two-Factor, Universal, Robust, Fast Distribution Learning Algorithm
Yi Hao, Ayush Jain, Alon Orlitsky, Vaishakh Ravindrakumar
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 TURF's split estimator to ADLS polynomial estimates | ADLS · Piecewise degree-d polynomials (P_{t,d}) | approximation factor: 3 -> (2+\alpha) | Improved |
| Use TURF instead of ADLS with cross-validated piece count | Beta, Gamma, and Gaussian mixtures · Noise-free and noisy mixture experiments | \ell_1 error | Improved |
| Increase polynomial degree from d=1 to d=2 | ADLS and TURF · Noise-free Beta, Gamma, and Gaussian mixtures | \ell_1 error | Improved |
| Increase polynomial degree from d=1 to d=2 | ADLS and TURF · Noisy Beta, Gamma, and Gaussian mixtures | \ell_1 error | Mixed |
Closest papers by meaning
- SURF: A Simple, Universal, Robust, Fast Distribution Learning Algorithm (NeurIPS 2020 · similarity 0.90)
- Nearly-Linear Time Private Hypothesis Selection with the Optimal Approximation Factor (NeurIPS 2025 · similarity 0.85)
- GraSS: Scalable Data Attribution with Gradient Sparsification and Sparse Projection (NeurIPS 2025 · similarity 0.85)
- On Socially Fair Low-Rank Approximation and Column Subset Selection (NeurIPS 2024 · similarity 0.83)
- Optimal Hypothesis Selection in (Almost) Linear Time (NeurIPS 2024 · similarity 0.83)
- Learning multivariate Gaussians with imperfect advice (ICML 2025 · 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.
