Can I read Mixture Models, Robustness, and Sum of Squares Proofs on EtoBox?

Mixture Models, Robustness, and Sum of Squares Proofs by Hopkins, Samuel B.; Li, Jerry is a scholarly article available to read on EtoBox.

What is Mixture Models, Robustness, and Sum of Squares Proofs about?

We use the Sum of Squares method to develop new efficient algorithms for learning well-separated mixtures of Gaussians and robust mean estimation, both in high dimensions, that substantially improve upon the statistical guarantees achieved by previous efficient algorithms. Firstly, we study mixtures of $k$ distributions in $d$ dimensions, where the means of every pair of distributions are separated by at least $k^{\varepsilon}$. In the special case of spherical Gaussian mixtures, we give a $(dk)^{O(1/\varepsilon^2)}$-time algorithm that learns the means assuming separation at least $k^{\varepsilon}$, for any $\varepsilon > 0$. This is the first algorithm to improve on greedy ("single-linkage") and spectral clustering, breaking a long-standing barrier for efficient algorithms at separation $k^{1/4}$. We also study robust estimation. When an unknown $(1-\varepsilon)$-fraction of $X_1,\ldots,X_n$ are chosen from a sub-Gaussian distribution with mean $\mu$ but the remaining points are chosen adversarially, we give an algorithm recovering $\mu$ to error $\varepsilon^{1-1/t}$ in time $d^{O(t^2)}$, so long as sub-Gaussian-ness up to $O(t)$ moments can be certified by a Sum of Squares proo

Author

Hopkins, Samuel B.; Li, Jerry

Published

2017

Language

EN