DeepAI AI Chat
Log In Sign Up

A Maximum Matching Algorithm for Basis Selection in Spectral Learning

by   Ariadna Quattoni, et al.

We present a solution to scale spectral algorithms for learning sequence functions. We are interested in the case where these functions are sparse (that is, for most sequences they return 0). Spectral algorithms reduce the learning problem to the task of computing an SVD decomposition over a special type of matrix called the Hankel matrix. This matrix is designed to capture the relevant statistics of the training sequences. What is crucial is that to capture long range dependencies we must consider very large Hankel matrices. Thus the computation of the SVD becomes a critical bottleneck. Our solution finds a subset of rows and columns of the Hankel that realizes a compact and informative Hankel submatrix. The novelty lies in the way that this subset is selected: we exploit a maximal bipartite matching combinatorial algorithm to look for a sub-block with full structural rank, and show how computation of this sub-block can be further improved by exploiting the specific structure of Hankel matrices.


page 1

page 2

page 3

page 4


Subset Selection for Matrices with Fixed Blocks

Subset selection for matrices is the task of extracting a column sub-mat...

Fast estimation method for rank of a high-dimensional sparse matrix

Numerical computing the rank of a matrix is a fundamental problem in sci...

Selecting Bases in Spectral learning of Predictive State Representations via Model Entropy

Predictive State Representations (PSRs) are powerful techniques for mode...

A fast spectral divide-and-conquer method for banded matrices

Based on the spectral divide-and-conquer algorithm by Nakatsukasa and Hi...

A combinatorial algorithm for computing the rank of a generic partitioned matrix with 2 × 2 submatrices

In this paper, we consider the problem of computing the rank of a block-...

Spectral Tensor Train Parameterization of Deep Learning Layers

We study low-rank parameterizations of weight matrices with embedded spe...