The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Jun. 04, 2024

Filed:

Mar. 17, 2020
Applicant:

Google Llc, Mountain View, CA (US);

Inventors:

Seungyeon Kim, New York, NY (US);

Jingzhao Zhang, Cambridge, MA (US);

Andreas Veit, New York, NY (US);

Sanjiv Kumar, Jericho, NY (US);

Sashank Reddi, Jersey City, NJ (US);

Praneeth Karimireddy, Renens, CH;

Assignee:

GOOGLE LLC, Mountain View, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06N 20/00 (2019.01); G06F 17/18 (2006.01); G06F 18/21 (2023.01); G06N 3/084 (2023.01);
U.S. Cl.
CPC ...
G06F 17/18 (2013.01); G06F 18/217 (2023.01); G06N 20/00 (2019.01); G06N 3/084 (2013.01);
Abstract

Generally, the present disclosure is directed to systems and methods that perform adaptive optimization with improved convergence properties. The adaptive optimization techniques described herein are useful in various optimization scenarios, including, for example, training a machine-learned model such as, for example, a neural network. In particular, according to one aspect of the present disclosure, a system implementing the adaptive optimization technique can, over a plurality of iterations, employ an adaptive per coordinate clipping threshold to clip a current first moment of the coordinate to obtain a current update value that enables faster convergence for the machine-learned model when the noise in the stochastic gradients is heavy tailed.


Find Patent Forward Citations

Loading…