Timezone: »

Constraints Based Convex Belief Propagation
Yaniv Tenzer · Alex Schwing · Kevin Gimpel · Tamir Hazan

Tue Dec 06 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #85 #None

Inference in Markov random fields subject to consistency structure is a fundamental problem that arises in many real-life applications. In order to enforce consistency, classical approaches utilize consistency potentials or encode constraints over feasible instances. Unfortunately this comes at the price of a serious computational bottleneck. In this paper we suggest to tackle consistency by incorporating constraints on beliefs. This permits derivation of a closed-form message-passing algorithm which we refer to as the Constraints Based Convex Belief Propagation (CBCBP). Experiments show that CBCBP outperforms the standard approach while being at least an order of magnitude faster.

Author Information

Yaniv Tenzer (The Hebrew University)

I am a PhD student in the Department of Statistics at the Hebrew University, Jerusalem. My main interests are in the fields of statistics, statistical learning and machine learning. Beforehand , I completed a master degree in statistics, at Tel-Aviv University, advised by Yoav Benjamini and held a research position at General Electric, specializing in machine vision and data driven algorithms.

Alex Schwing (University of Illinois at Urbana-Champaign)
Kevin Gimpel (Carnegie Mellon University)
Tamir Hazan (Technion)

More from the Same Authors