all AI news
Path Independent Equilibrium Models Can Better Exploit Test-Time Computation. (arXiv:2211.09961v1 [cs.LG])
Nov. 21, 2022, 2:11 a.m. | Cem Anil, Ashwini Pokle, Kaiqu Liang, Johannes Treutlein, Yuhuai Wu, Shaojie Bai, Zico Kolter, Roger Grosse
cs.LG updates on arXiv.org arxiv.org
Designing networks capable of attaining better performance with an increased
inference budget is important to facilitate generalization to harder problem
instances. Recent efforts have shown promising results in this direction by
making use of depth-wise recurrent networks. We show that a broad class of
architectures named equilibrium models display strong upwards generalization,
and find that stronger performance on harder examples (which require more
iterations of inference to get correct) strongly correlates with the path
independence of the system -- its …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Senior ML Researcher - 3D Geometry Processing | 3D Shape Generation | 3D Mesh Data
@ Promaton | Europe
Director, Global Procurement Data Analytics
@ Alcon | Fort Worth - Main
Backend Software Engineer, Airbnb for Real Estate
@ Airbnb | United States
Data Scientist
@ Exoticca | Barcelona, Catalonia, Spain - Remote
ESG Data Analytics Summer Associate (Intern)
@ Apex Clean Energy | Charlottesville, VA, United States
Team Lead, Machine Learning
@ Prenuvo | Vancouver, British Columbia, Canada