Web: http://arxiv.org/abs/2205.01435

May 4, 2022, 1:11 a.m. | Sean Parker, Sami Alabed, Eiko Yoneki

cs.LG updates on arXiv.org arxiv.org

We explored the use of reinforcement learning (RL) agents that can learn to
perform neural network subgraph transformations, without the need of expertly
designed heuristics to achieve a high level of performance. Reducing compute
requirements of deep learning models is a focus of extensive research and many
systems, optimisations and just-in-time (JIT) compilers have been proposed to
decrease runtime.


Recent work has aimed to apply reinforcement learning to computer systems
with some success, especially using model-free RL techniques. Model-based
reinforcement …

arxiv models network neural neural network transformation

More from arxiv.org / cs.LG updates on arXiv.org

Director, Applied Mathematics & Computational Research Division

@ Lawrence Berkeley National Lab | Berkeley, Ca

Business Data Analyst

@ MainStreet Family Care | Birmingham, AL

Assistant/Associate Professor of the Practice in Business Analytics

@ Georgetown University McDonough School of Business | Washington DC

Senior Data Science Writer

@ NannyML | Remote

Director of AI/ML Engineering

@ Armis Industries | Remote (US only), St. Louis, California

Digital Analytics Manager

@ Patagonia | Ventura, California