Web: http://arxiv.org/abs/2206.06531

June 20, 2022, 1:11 a.m. | Dounia Lakhmiri, Dominique Orban, Andrea Lodi

cs.LG updates on arXiv.org arxiv.org

We consider the problem of training a deep neural network with nonsmooth
regularization to retrieve a sparse and efficient sub-structure. Our
regularizer is only assumed to be lower semi-continuous and prox-bounded. We
combine an adaptive quadratic regularization approach with proximal stochastic
gradient principles to derive a new solver, called SR2, whose convergence and
worst-case complexity are established without knowledge or approximation of the
gradient's Lipschitz constant. We formulate a stopping criteria that ensures an
appropriate first-order stationarity measure converges to …

arxiv ml optimization stochastic

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