Barrier Frank-Wolfe for Marginal Inference

Author name not available (Why is that?)

Publication date: 6 November 2015

Abstract: We introduce a globally-convergent algorithm for optimizing the tree-reweighted (TRW) variational objective over the marginal polytope. The algorithm is based on the conditional gradient method (Frank-Wolfe) and moves pseudomarginals within the marginal polytope through repeated maximum a posteriori (MAP) calls. This modular structure enables us to leverage black-box MAP solvers (both exact and approximate) for variational inference, and obtains more accurate results than tree-reweighted algorithms that optimize over the local consistency relaxation. Theoretically, we bound the sub-optimality for the proposed algorithm despite the TRW objective having unbounded gradients at the boundary of the marginal polytope. Empirically, we demonstrate the increased quality of results found by tightening the relaxation over the marginal polytope as well as the spanning tree polytope on synthetic and real-world instances.

Has companion code repository: https://github.com/clinicalml/fw-inference

This page was built for publication: Barrier Frank-Wolfe for Marginal Inference

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6267171)