Skip to yearly menu bar Skip to main content

Workshop: OPT 2021: Optimization for Machine Learning

Structured Low-Rank Tensor Learning

Jayadev Naram · Tanmay Sinha · Pawan Kumar


We consider the problem of learning low-rank tensors from partial observations with structural constraints and propose a novel factorization of such tensors, which leads to a simpler optimization problem. The resulting problem is an optimization problem on manifolds. We develop first-order and second-order Riemannian optimization algorithms to solve it. The duality gap for the resulting problem is derived, and we experimentally verify the correctness of the proposed algorithm. We demonstrate the algorithm on Nonnegative constraints and Hankel constraints.

Chat is not available.