Title: LAROS: a convex optimization approach for feature extraction
Speaker: Dr. Xuan Vinh Doan
Affiliation: Warwick Business School – University of Warwick
Location: Room 572A Huxley Building
Time: 3:00pm

Abstract. We propose a convex optimization formulation using nuclear norm and $ell_1$-norm to find a large approximately rank-one submatrix (LAROS) for a given matrix. We are able to characterize the low-rank and sparsity structure of the resulting solutions. We show that our model can recover low-rank submatrices for matrices with subgaussian random noises. We solve the proposed model using a proximal point algorithm and show that it can be applied to applications in feature extraction. This is joint work with Stephen Vavasis and Kim-Chuan Toh.

About the speaker.