Robust Learning of Mixtures of Gaussians
Daniel M. Kane
2021年份
12被引次数
15顶会引用
摘要
We resolve one of the major outstanding problems in robust statistics. In particular, if X is an evenly weighted mixture of two arbitrary d-dimensional Gaussians, we devise a polynomial time algorithm that given access to samples from X an ∊-fraction of which have been adversarially corrupted, learns X to error poly(∊) in total variation distance.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式，引用它的顶会 Paper 也一样。你提问，回答直接引用原文。
引用它的顶会 Paper15
- Learning Mixtures of Gaussians Using the DDPM ObjectiveKulin Shah, Sitan Chen, Adam R. KlivansNeurIPS 2023 · 被引用 69 次
- Robustly learning mixtures of k arbitrary GaussiansAinesh Bakshi, Ilias Diakonikolas, He Jia, Daniel M. Kane 等STOC 2022 · 被引用 21 次
- Settling the robust learnability of mixtures of GaussiansAllen Liu, Ankur MoitraSTOC 2021 · 被引用 14 次
- Online and Distribution-Free Robustness: Regression and Contextual Bandits with Huber ContaminationSitan Chen, Frederic Koehler, Ankur Moitra, Morris YauFOCS 2021 · 被引用 14 次
- Clustering mixture models in almost-linear time via list-decodable mean estimationIlias Diakonikolas, Daniel M. Kane, Daniel Kongsgaard, Jerry Li 等STOC 2022 · 被引用 6 次
相关 Paper
- List-Decodable Sparse Mean EstimationShiwei Zeng, Jie ShenNeurIPS 2022 · 被引用 13 次
- Robust Gaussian Covariance Estimation in Nearly-Matrix Multiplication TimeJerry Li, Guanghao YeNeurIPS 2020 · 被引用 13 次
- Robust Model Selection and Nearly-Proper Learning for GMMsAllen Liu, Jerry Li, Ankur MoitraNeurIPS 2022 · 被引用 5 次
- List-decodable covariance estimationMisha Ivkov, Pravesh K. KothariSTOC 2022 · 被引用 5 次
- Robust Learning of Fixed-Structure Bayesian Networks in Nearly-Linear TimeYu Cheng, Honghao LinICLR 2021
