On the robust learning mixtures of linear regressions
Huang, Ying, Liang Chen · arXiv (Cornell University) · 2023
In this note, we consider the problem of robust learning mixtures of linear regressions. We connect mixtures of linear regressions and mixtures of Gaussians with a simple thresholding, so that a quasi-polynomial time algorithm can be obtained under some mild separation condition. This algorithm has significantly better robustness than the previous result.