Results 1 
4 of
4
Tractable semisupervised learning of complex structured prediction models
 In ECML
, 2013
"... Abstract. Semisupervised learning has been widely studied in the literature. However, most previous works assume that the output structure is simple enough to allow the direct use of tractable inference/learning algorithms (e.g., binary label or linear chain). Therefore, these methods cannot be ap ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
(Show Context)
Abstract. Semisupervised learning has been widely studied in the literature. However, most previous works assume that the output structure is simple enough to allow the direct use of tractable inference/learning algorithms (e.g., binary label or linear chain). Therefore, these methods cannot be applied to problems with complex structure. In this paper, we propose an approximate semisupervised learning method that uses piecewise training for estimating the model weights and a dual decomposition approach for solving the inference problem of finding the labels of unlabeled data subject to domain specific constraints. This allows us to extend semisupervised learning to general structured prediction problems. As an example, we apply this approach to the problem of multilabel classification (a fully connected pairwise Markov random field). Experimental results on benchmark data show that, in spite of using approximations, the approach is effective and yields good improvements in generalization performance over the plain supervised method. In addition, we demonstrate that our inference engine can be applied to other semisupervised learning frameworks, and extends them to solve problems with complex structure.
AD³: Alternating Directions Dual Decomposition for MAP Inference in Graphical Models
"... We present AD³, a new algorithm for approximate maximum a posteriori (MAP) inference on factor graphs, based on the alternating directions method of multipliers. Like other dual decomposition algorithms, AD³ has a modular architecture, where local subproblems are solved independently, and their solu ..."
Abstract
 Add to MetaCart
We present AD³, a new algorithm for approximate maximum a posteriori (MAP) inference on factor graphs, based on the alternating directions method of multipliers. Like other dual decomposition algorithms, AD³ has a modular architecture, where local subproblems are solved independently, and their solutions are gathered to compute a global update. The key characteristic of AD3 is that each local subproblem has a quadratic regularizer, leading to faster convergence, both theoretically and in practice. We provide closedform solutions for these AD³ subproblems for binary pairwise factors and factors imposing firstorder logic constraints. For arbitrary factors (large or combinatorial), we introduce an active set method which requires only an oracle for computing a local MAP configuration, making AD³ applicable to a wide range of problems. Experiments on synthetic and realworld problems show that AD³ compares favorably with the stateoftheart.
MIKSIK ET AL.: DISTRIBUTED INFERENCE IN RANDOM FIELDS 1 Distributed NonConvex ADMMinference in Largescale Random Fields
"... We propose a parallel and distributed algorithm for solving discrete labeling problems in large scale random fields. Our approach is motivated by the following observations: i) very large scale image and video processing problems, such as labeling dozens of million pixels with thousands of labels, a ..."
Abstract
 Add to MetaCart
(Show Context)
We propose a parallel and distributed algorithm for solving discrete labeling problems in large scale random fields. Our approach is motivated by the following observations: i) very large scale image and video processing problems, such as labeling dozens of million pixels with thousands of labels, are routinely faced in many application domains; ii) the computational complexity of the current stateoftheart inference algorithms makes them impractical to solve such large scale problems; iii) modern parallel and distributed systems provide high computation power at low cost. At the core of our algorithm is a treebased decomposition of the original optimization problem which is solved using a non convex form of the method of alternating direction method of multipliers (ADMM). This allows efficient parallel solving of resulting subproblems. We evaluate the efficiency and accuracy offered by our algorithm on several benchmark lowlevel vision problems, on both CPU and Nvidia GPU. We consistently achieve a factor of speedup compared to dual decomposition (DD) approach and other ADMMbased approaches. 1