Convergence-Aware Neural Network Training
- Title
- Convergence-Aware Neural Network Training
- Author
- 서지원
- Keywords
- Convergence; Training; Neurons; Correlation; Monitoring; Kernel; History
- Issue Date
- 2020-07
- Publisher
- IEEE
- Citation
- 2020 57th ACM/IEEE Design Automation Conference (DAC), page. 1-6
- Abstract
- Training a deep neural network (DNN) is expensive, requiring a large amount of computation time. While the training overhead is high, not all computation in DNN training is equal. Some parameters converge faster and thus their gradient computation may contribute little to the parameter update; in nearstationary points a subset of parameters may change very little. In this paper we exploit the parameter convergence to optimize gradient computation in DNN training. We design a light-weight monitoring technique to track the parameter convergence; we prune the gradient computation stochastically for a group of semantically related parameters, exploiting their convergence correlations. These techniques are efficiently implemented in existing GPU kernels. In our evaluation the optimization techniques substantially and robustly improve the training throughput for four DNN models on three public datasets.
- URI
- https://ieeexplore.ieee.org/document/9218518https://repository.hanyang.ac.kr/handle/20.500.11754/169267
- ISBN
- 978-1-7281-1085-1
- ISSN
- 0738-100X
- DOI
- 10.1109/DAC18072.2020.9218518
- Appears in Collections:
- COLLEGE OF ENGINEERING[S](공과대학) > COMPUTER SCIENCE(컴퓨터소프트웨어학부) > Articles
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML