US 12,136,038 B2
Gradient pruning for efficient training of machine learning models
Yash Sanjay Bhalgat, San Diego, CA (US); Jin Won Lee, San Diego, CA (US); Jamie Menjay Lin, San Diego, CA (US); Fatih Murat Porikli, Carlsbad, CA (US); and Chirag Sureshbhai Patel, San Diego, CA (US)
Assigned to QUALCOMM Incorporated, San Diego, CA (US)
Filed by QUALCOMM Incorporated, San Diego, CA (US)
Filed on Feb. 12, 2021, as Appl. No. 17/175,487.
Prior Publication US 2022/0261648 A1, Aug. 18, 2022
Int. Cl. G06N 3/082 (2023.01); G06F 18/214 (2023.01); G06N 3/098 (2023.01); G06N 20/00 (2019.01)
CPC G06N 3/082 (2013.01) [G06F 18/2148 (2023.01); G06N 3/098 (2023.01); G06N 20/00 (2019.01)] 30 Claims
OG exemplary drawing
 
1. A method for training a machine learning model, comprising:
computing using a first batch of training data, a first gradient tensor comprising a gradient for each parameter of a parameter tensor for a machine learning model;
identifying a first subset of gradients in the first gradient tensor based on evaluating each respective gradient of the first gradient tensor using a first gradient criteria; and
updating a first subset of parameters in the parameter tensor based on the first subset of gradients.