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

Nov 14, 2018.   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... Continue

WACV 18 Tutorial on Optimization Methods for Deep Learning - Theory and Practice

Mar 12, 2018.   This is the webpage for the tutorial “Optimization Methods for Deep Learning - Theory and Practice” to be organized in the Winter Conf. on Applications of Computer Vision (WACV) 18. Here is the schedule for... Continue

Nonsmooth Frank-Wolfe algorithm and Coresets

Aug 21, 2017.   In this post we will see how Frank-Wolfe (FW) algorithm (aka Conditional Gradient algorithm) can be generalized to nonsmooth problems (see here for the paper corresponding to this post). By nonsmooth we mean optimization problems... Continue