Smooth and strong: MAP inference with linear convergence

Ofer Meshi, Mehrdad Mahdavi, Alexander G. Schwing

Research output: Contribution to journalConference articlepeer-review

25 Scopus citations


Maximum a-posteriori (MAP) inference is an important task for many applications. Although the standard formulation gives rise to a hard combinatorial optimization problem, several effective approximations have been proposed and studied in recent years. We focus on linear programming (LP) relaxations, which have achieved state-of-the-art performance in many applications. However, optimization of the resulting program is in general challenging due to non-smoothness and complex non-separable constraints. Therefore, in this work we study the benefits of augmenting the objective function of the relaxation with strong convexity. Specifically, we introduce strong convexity by adding a quadratic term to the LP relaxation objective. We provide theoretical guarantees for the resulting programs, bounding the difference between their optimal value and the original optimum. Further, we propose suitable optimization algorithms and analyze their convergence.

Original languageEnglish (US)
Pages (from-to)298-306
Number of pages9
JournalAdvances in Neural Information Processing Systems
StatePublished - 2015
Event29th Annual Conference on Neural Information Processing Systems, NIPS 2015 - Montreal, Canada
Duration: Dec 7 2015Dec 12 2015

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing


Dive into the research topics of 'Smooth and strong: MAP inference with linear convergence'. Together they form a unique fingerprint.

Cite this