Title | ||
---|---|---|
AUTOMATIC DIFFERENTIATION FOR RIEMANNIAN OPTIMIZATION ON LOW-RANK MATRIX AND TENSOR-TRAIN MANIFOLDS |
Abstract | ||
---|---|---|
In scientific computing and machine learning applications, matrices and more general multidimensional arrays (tensors) can often be approximated with the help of low-rank decompositions. Since matrices and tensors of fixed rank form smooth Riemannian manifolds, one of the popular tools for finding low-rank approximations is to use Riemannian optimization. Nevertheless, efficient implementation of Riemannian gradients and Hessians, required in Riemannian optimization algorithms, can be a nontrivial task in practice. Moreover, in some cases, analytic formulas are not even available. In this paper, we build upon automatic differentiation and propose a method that, given an implementation of the function to be minimized, efficiently computes Riemannian gradients and matrix-by-vector products between an approximate Riemannian Hessian and a given vector. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1137/20M1356774 | SIAM JOURNAL ON SCIENTIFIC COMPUTING |
Keywords | DocType | Volume |
automatic differentiation, Riemannian optimization, low-rank approximation, tensor-train decomposition | Journal | 44 |
Issue | ISSN | Citations |
2 | 1064-8275 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Alexander Novikov | 1 | 0 | 0.34 |
Maxim Rakhuba | 2 | 0 | 1.69 |
Ivan V. Oseledets | 3 | 306 | 41.96 |