Rares Buhai
@raresbuhai.bsky.social
postdoc at EPFL. raresbuhai.com.
Reposted by Rares Buhai
Excited to present at #NeurIPS2024 our work on robust mixture learning!
How hard is mixture learning when (a lot of) outliers are present? We show that it's easier than it seems!
Join us at the poster session (Wed, 16:30 PT, West Ballroom A-D #5710).
How hard is mixture learning when (a lot of) outliers are present? We show that it's easier than it seems!
Join us at the poster session (Wed, 16:30 PT, West Ballroom A-D #5710).
December 10, 2024 at 8:31 PM
Excited to present at #NeurIPS2024 our work on robust mixture learning!
How hard is mixture learning when (a lot of) outliers are present? We show that it's easier than it seems!
Join us at the poster session (Wed, 16:30 PT, West Ballroom A-D #5710).
How hard is mixture learning when (a lot of) outliers are present? We show that it's easier than it seems!
Join us at the poster session (Wed, 16:30 PT, West Ballroom A-D #5710).
In arxiv.org/abs/2411.12438 we obtain new results for clustering mixtures of non-spherical Gaussians! Highlight: poly(d) * f(w_min) algorithm for mixtures of arbitrary zero-mean TVD-separated Gaussians. W/ Prashanti Anderson, Mitali Bafna, @praveshkkothari.bsky.social, and David Steurer.
Dimension Reduction via Sum-of-Squares and Improved Clustering Algorithms for Non-Spherical Mixtures
We develop a new approach for clustering non-spherical (i.e., arbitrary component covariances) Gaussian mixture models via a subroutine, based on the sum-of-squares method, that finds a low-dimensiona...
arxiv.org
November 26, 2024 at 11:04 AM
In arxiv.org/abs/2411.12438 we obtain new results for clustering mixtures of non-spherical Gaussians! Highlight: poly(d) * f(w_min) algorithm for mixtures of arbitrary zero-mean TVD-separated Gaussians. W/ Prashanti Anderson, Mitali Bafna, @praveshkkothari.bsky.social, and David Steurer.