Oct. 10, 2022, 1:13 a.m. | Arjun Krishnakumar, Colin White, Arber Zela, Renbo Tu, Mahmoud Safari, Frank Hutter

stat.ML updates on arXiv.org arxiv.org

Zero-cost proxies (ZC proxies) are a recent architecture performance
prediction technique aiming to significantly speed up algorithms for neural
architecture search (NAS). Recent work has shown that these techniques show
great promise, but certain aspects, such as evaluating and exploiting their
complementary strengths, are under-studied. In this work, we create
NAS-Bench-Suite: we evaluate 13 ZC proxies across 28 tasks, creating by far the
largest dataset (and unified codebase) for ZC proxies, enabling
orders-of-magnitude faster experiments on ZC proxies, while avoiding …

arxiv cost nas proxies research

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

Lead Data Engineer

@ JPMorgan Chase & Co. | Jersey City, NJ, United States

Senior Machine Learning Engineer

@ TELUS | Vancouver, BC, CA

CT Technologist - Ambulatory Imaging - PRN

@ Duke University | Morriville, NC, US, 27560

BH Data Analyst

@ City of Philadelphia | Philadelphia, PA, United States