### Approximation algorithms for classification problems with pairwise relationships: metric labeling and Markov random fieldsApproximation algorithms for classification problems with pairwise relationships: metric labeling and Markov random fields

Access Restriction
Subscribed

 Author Kleinberg, Jon ♦ Tardos, va Source ACM Digital Library Content type Text Publisher Association for Computing Machinery (ACM) File Format PDF Copyright Year ©2002 Language English
 Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science Subject Keyword Approximation algorithms ♦ Markov random fields ♦ Classification ♦ Metric labeling Abstract In a traditional classification problem, we wish to assign one of k labels (or classes) to each of n objects, in a way that is consistent with some observed data that we have about the problem. An active line of research in this area is concerned with classification when one has information about pairwise relationships among the objects to be classified; this issue is one of the principal motivations for the framework of Markov random fields, and it arises in areas such as image processing, biometry, and document analysis. In its most basic form, this style of analysis seeks to find a classification that optimizes a combinatorial function consisting of assignment costs---based on the individual choice of label we make for each object---and separation costs---based on the $\textit{pair}$ of choices we make for two "related" objects.We formulate a general classification problem of this type, the metric labeling problem; we show that it contains as special cases a number of standard classification frameworks, including several arising from the theory of Markov random fields. From the perspective of combinatorial optimization, our problem can be viewed as a substantial generalization of the multiway cut problem, and equivalent to a type of uncapacitated quadratic assignment problem.We provide the first nontrivial polynomial-time approximation algorithms for a general family of classification problems of this type. Our main result is an $\textit{O}(log$ $\textit{k}$ log log $\textit{k})-approximation$ algorithm for the metric labeling problem, with respect to an arbitrary metric on a set of $\textit{k}$ labels, and an arbitrary weighted graph of relationships on a set of objects. For the special case in which the labels are endowed with the uniform metric---all distances are the same---our methods provide a 2-approximation algorithm. ISSN 00045411 Age Range 18 to 22 years ♦ above 22 year Educational Use Research Education Level UG and PG Learning Resource Type Article Publisher Date 2002-09-01 Publisher Place New York e-ISSN 1557735X Journal Journal of the ACM (JACM) Volume Number 49 Issue Number 5 Page Count 24 Starting Page 616 Ending Page 639

#### Open content in new tab

Source: ACM Digital Library