Explicitly Imposing Constraints in Deep Networks Via Conditional Gradients Gives Improved Generalization and Faster Convergence

This is the webpage that contains details including presentation and video of our paper titled, “Explicitly Imposing Constraints in Deep Networks Via Conditional Gradients Gives Improved Generalization and Faster Convergence” that will be presented at the AAAI 2019 conference.

Video:

(Slides)