DEPARTAMENTO DE MATEMÁTICA – CFM / UFSC

Seminário de Otimização & Problemas Inversos

Título: A two-phase rank-based algorithm for low-rank matrix completion

Palestrante: Douglas S. Gonçalves (UFSC)

Resumo: Matrix completion aims to recover an unknown low-rank matrix from a small subset of its entries. In many applications, the rank of the unknown target matrix is known in advance. In this paper, first, we revisit a recently proposed rank-based heuristic for “known- rank” matrix completion and establish a condition under which the generated sequence is quasi-Fejér convergent to the solution set. Then, by including an acceleration mechanism similar to Nesterov’s acceleration, we obtain a new heuristic. Even though the convergence of this new heuristic cannot be granted in general, it turns out that it can be very useful as a warm-start phase (phase one), providing a suitable estimate for the regularization parameter and a good starting point to an accelerated proximal gradient algorithm (phase two) aimed to solve a nuclear-norm regularized problem. Numerical experiments with both synthetic and real data show that the resulting two-phase rank-based algorithm can recover low-rank matrices, with relatively high precision, faster than other well-established matrix completion algorithms.

Data: Segunda-feira, 24 de Outubro  de 2022 , 14h

Local: Auditório Airton Silva, Departamento de Matemática / CFM

Maiores informações:  http://mtm.ufsc.br/~maicon/seminar

E. Krukoski