all AI news
Adapprox: Adaptive Approximation in Adam Optimization via Randomized Low-Rank Matrices
March 25, 2024, 4:41 a.m. | Pengxiang Zhao, Ping Li, Yingjie Gu, Yi Zheng, Stephan Ludger K\"olker, Zhefeng Wang, Xiaoming Yuan
cs.LG updates on arXiv.org arxiv.org
Abstract: As deep learning models exponentially increase in size, optimizers such as Adam encounter significant memory consumption challenges due to the storage of first and second moment data. Current memory-efficient methods like Adafactor and CAME often compromise accuracy with their matrix factorization techniques. Addressing this, we introduce Adapprox, a novel approach that employs randomized low-rank matrix approximation for a more effective and accurate approximation of Adam's second moment. Adapprox features an adaptive rank selection mechanism, finely …
abstract accuracy adam approximation arxiv challenges consumption cs.cl cs.lg current data deep learning factorization low math.oc matrix memory memory consumption optimization storage type via
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Developer AI Senior Staff Engineer, Machine Learning
@ Google | Sunnyvale, CA, USA; New York City, USA
Engineer* Cloud & Data Operations (f/m/d)
@ SICK Sensor Intelligence | Waldkirch (bei Freiburg), DE, 79183