Huang, S.
, Hoskins, B.
, Daniels, M.
, Stiles, M.
and Adam, G.
(2020),
Streaming Batch Gradient Tracking for Neural Network Training, AAAI Conference on Artificial Intelligence, New York, NY, [online], https://doi.org/10.1609/aaai.v34i10.7178
(Accessed April 25, 2024)
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
Streaming Batch Gradient Tracking for Neural Network Training
Published
Author(s)
, , , ,
Abstract
Faster and more energy efficient hardware accelerators are critical for machine learning on very large datasets. The energy cost of performing vector-matrix multiplication and repeatedly moving neural network models in and out of memory motivates a search for alternative hardware and algorithms. We propose to use streaming batch principal component analysis (SBPCA) to compress batch data during training by using a rank-k approximation of the total batch update. This approach yields comparable training performance to minibatch gradient descent (MBGD) at the same batch size while reducing overall memory and compute requirements.Volume
34
Issue
10
Conference Dates
February 7-12, 2020
Conference Location
New York, NY
Conference Title
AAAI Conference on Artificial Intelligence
Pub Type
Conferences
Download Paper
Citation
Created April 2, 2020, Updated July 8, 2020