Web: http://arxiv.org/abs/2206.07839

June 17, 2022, 1:10 a.m. | Tianlong Chen, Huan Zhang, Zhenyu Zhang, Shiyu Chang, Sijia Liu, Pin-Yu Chen, Zhangyang Wang

cs.LG updates on arXiv.org arxiv.org

Certifiable robustness is a highly desirable property for adopting deep
neural networks (DNNs) in safety-critical scenarios, but often demands tedious
computations to establish. The main hurdle lies in the massive amount of
non-linearity in large DNNs. To trade off the DNN expressiveness (which calls
for more non-linearity) and robustness certification scalability (which prefers
more linearity), we propose a novel solution to strategically manipulate
neurons, by "grafting" appropriate levels of linearity. The core of our
proposal is to first linearize insignificant …

arxiv lg pruning robustness

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

Machine Learning Researcher - Saalfeld Lab

@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia

Project Director, Machine Learning in US Health

@ ideas42.org | Remote, US

Data Science Intern

@ NannyML | Remote

Machine Learning Engineer NLP/Speech

@ Play.ht | Remote

Research Scientist, 3D Reconstruction

@ Yembo | Remote, US

Clinical Assistant or Associate Professor of Management Science and Systems

@ University at Buffalo | Buffalo, NY