← Search

D. Khuê Lê-Huu

2 accepted papers

2021

Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond

NeurIPS 2021poster

We introduce regularized Frank-Wolfe, a general and effective algorithm for inference and learning of dense conditional random fields (CRFs). The algorithm optimizes a nonconvex continuous relaxation of the CRF inference problem using vanilla Frank-Wolfe with approximate updates, which are equivalen…