Title: Recovery of a mixture of Gaussians by sum-of-norms clustering
| Speaker: | Tao Jiang |
| Affiliation: | University of Waterloo |
| Room: | MC 5417 |
Abstract:
Sum-of-norms clustering is a method for assigning n points in Rd to K clusters, 1 ≤ K ≤ n, using convex optimization. Recently, Panahi et al. proved that sum-of-norms clustering is guaranteed to recover a mixture of Gaussians under the restriction that the number of samples is not too large. In this talk, I will present how we lift this restriction, i.e., show that sum-of-norms clustering with equal weights can recover a mixture of Gaussians even as the number of samples tends to infinity. Moreover, I will go through the proof in the paper and an interesting characterization of clusters computed by sum-of-norms clustering that was developed inside a proof of the agglomeration conjecture by Chiquet et al. Joint work with Stephen Vavasis and Chen Wen Zhai.