Streaming Batch Gradient Tracking for Neural Network Training (Student Abstract)

Authors

  • Siyuan Huang George Washington University
  • Brian D. Hoskins National Institute of Standards and Technology
  • Matthew W. Daniels National Institute of Standards and Technology
  • Mark D. Stiles National Institute of Standards and Technology
  • Gina C. Adam George Washington University

DOI:

https://doi.org/10.1609/aaai.v34i10.7178

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.

Downloads

Published

2020-04-03

How to Cite

Huang, S., Hoskins, B. D., Daniels, M. W., Stiles, M. D., & Adam, G. C. (2020). Streaming Batch Gradient Tracking for Neural Network Training (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 34(10), 13813-13814. https://doi.org/10.1609/aaai.v34i10.7178

Issue

Section

Student Abstract Track