Patent · US Active

Training SVMs with parallelized stochastic gradient descent

US8626677B2 · kind B2 · utility

7Cited by

0References

18Claims

0Family size

Assignee

Microsoft Corporation · US

Inventors

Weizhu Chen · Beijing, CN
Gang Wang · San Diego, US
Zheng Chen · Beijing, CN

Key dates

Filing date	May 28, 2010
Grant date	Jan 7, 2014
Priority date	—
Expiry date	May 7, 2032

Classification

Technology area (CPC G)Physics
CPC primaryG06N20/10
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Techniques for training a non-linear support vector machine utilizing a stochastic gradient descent algorithm are provided. The computations of the stochastic gradient descent algorithm are parallelized via a number of processors. Calculations of the stochastic gradient descent algorithm on a particular processor may be combined according to a packing strategy before communicating the results of the calculations with the other processors.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.