Research map / Learning theory and algorithms / Sample complexity
A Fourier Approach to Mixture Learning
Mingda Qiao, Guru Guruganesh, Ankit Singh Rawat, Kumar Avinava Dubey, Manzil Zaheer
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 |
|---|---|---|---|
| Fourier-based estimation at chosen frequencies gives poly(k)-time learning at separation d/sqrt(log k) | Fourier mixture learner · spherical Gaussian mixtures, d = O(log k/log log k) | required separation | Improved |
| Lower bound: separation o(d/sqrt(log k)) | any learner · spherical Gaussian mixtures in low dimension | parameter identifiability | Hurt |
| Extend algorithm from Gaussians to translated copies of a distribution with slowly decaying Fourier transform | Fourier mixture learner · general location mixtures | learnability | Improved |
| Compare to prior algorithms with arbitrarily small separation | Fourier mixture learner · spherical Gaussian mixtures | runtime: e^{Omega(k)} -> O~(k^3)·f(d, Delta, epsilon) | Improved |
Closest papers by meaning
- Learning Mixtures of Gaussians Using the DDPM Objective (NeurIPS 2023 · similarity 0.90)
- Learning Mixture of Gaussians with Streaming Data (NeurIPS 2017 · similarity 0.90)
- Is $\sqrt{d}$ Separation Necessary for Gradient EM to Learn Gaussian Mixtures in High Dimensions? (NeurIPS 2026 · similarity 0.87)
- Toward Global Convergence of Gradient EM for Over-Paramterized Gaussian Mixture Models (NeurIPS 2024 · similarity 0.86)
- Sample-Efficient Private Learning of Mixtures of Gaussians (NeurIPS 2024 · similarity 0.86)
- Gaussian Mixture Models in Hilbert Spaces via Kernel Methods (NeurIPS 2026 · similarity 0.85)
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.
