Learning Mixtures of Gaussians with Censored Data
Not on the map. Why?
Abstract (arXiv)
We study the problem of learning mixtures of Gaussians with censored data. Statistical learning with censored data is a classical problem, with numerous practical applications, however, finite-sample guarantees for even simple latent variable models such as Gaussian mixtures are missing. Formally, we are given censored data from a mixture of univariate Gaussians sumi=1k wi N(μi,σ2), i.e. the sample is observed only if it lies inside a set S. The goal is to learn the weights wi and the means μi. We propose an algorithm that takes only frac1varepsilonO(k) samples to estimate the weights wi and the means μi within varepsilon error.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 15 of its 40 references that are in the map. First posted on arXiv 6 May 2023.
Builds on
15 of 40 references.
References · 15
- 2016Robust Estimators in High Dimensions without the Computational Intractabilitycited by 209
- 2016Agnostic Estimation of Mean and Covariancecited by 131
- 2019Recent Advances in Algorithmic High-Dimensional Robust Statisticscited by 100
- 2017Being Robust (in High Dimensions) Can Be Practicalcited by 83
- 2021Robust and Differentially Private Mean Estimationcited by 66
- 2021Efficient Mean Estimation with Pure Differential Privacy via a Sum-of-Squares Exponential Mechanismcited by 50
- 2016Ten Steps of EM Suffice for Mixtures of Two Gaussianscited by 40
- 2017Robustly Learning a Gaussian: Getting Optimal Error, Efficientlycited by 39
- 2016Global analysis of Expectation Maximization for mixtures of two Gaussianscited by 31
- 2017On Learning Mixtures of Well-Separated Gaussianscited by 30
- 2014Tight bounds for learning a mixture of two gaussianscited by 29
- 2018Efficient Statistics, in High Dimensions, from Truncated Samplescited by 28
3 more
- 2020Computationally and Statistically Efficient Truncated Regressioncited by 23
- 2019On the Analysis of EM for truncated mixtures of two Gaussianscited by 10
- 2022A Fourier Approach to Mixture Learningcited by 5
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.