US Patent:
20180114145, Apr 26, 2018
Inventors:
- Mountain View CA, US
Sanjiv KUMAR - Jericho NY, US
Xinnan YU - Forest Hills NY, US
Krzysztof Marcin CHOROMANSKI - New York NY, US
Ananda Theertha SURESH - New York NY, US
International Classification:
G06N 99/00
G06F 17/16
G06F 17/14
G06F 17/17
Abstract:
Techniques of generating input for a kernel-based machine learning system that uses a kernel to perform classification operations on data involve generating unbiased estimators for gaussian kernels according to a new framework called Structured Orthogonal Random Features (SORF). The unbiased estimator Kto the kernel involves a linear transformation matrix Wcomputed using products of a set of pairs of matrices, each pair including an orthogonal matrix and respective diagonal matrix whose elements are real numbers following a specified probability distribution. Typically, the orthogonal matrix is a Walsh-Hadamard matrix, the specified probability distribution is a Rademacher distribution, and there are at least two, usually three, pairs of matrices multiplied together to form the linear transformation matrix W.