Web: http://arxiv.org/abs/2205.09615

June 23, 2022, 1:11 a.m. | Ivan Karpukhin, Stanislav Dereka, Sergey Kolesnikov

cs.LG updates on arXiv.org arxiv.org

Classification tasks are usually evaluated in terms of accuracy. However,
accuracy is discontinuous and cannot be directly optimized using gradient
ascent. Popular methods minimize cross-entropy, Hinge loss, or other surrogate
losses, which can lead to suboptimal results. In this paper, we propose a new
optimization framework by introducing stochasticity to a model's output and
optimizing expected accuracy, i.e. accuracy of the stochastic model. Extensive
experiments on image classification show that the proposed optimization method
is a powerful alternative to widely …

accuracy arxiv lg

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