M best solutions over Graphical Models
نویسندگان
چکیده
Bucket elimination is an algorithmic framework that generalizes dynamic programming to accommodate many problem-solving and reasoning tasks. In particular, it can be used for any combinatorial optimization task such as finding most probable configurations in a Bayesian network. In this paper we present a new algorithm elim-m-opt, extending bucket elimination for the task of finding m best solutions for an optimization task for any value of m. We formulate our algorithm using general notion of combination and marginalization operators and show that our approach is sound. We provide complexity analysis and compare it with related work. Potential extension to the mini-bucket framework and its impact on heuristic-search for m-best are discussed.
منابع مشابه
SEARCHING FOR M BEST SOLUTIONS IN GRAPHICAL MODELS Searching For M Best Solutions In Graphical Models
The paper focuses on finding the m best solutions to combinatorial optimization problems using best-first or depth-first branch and bound search. Specifically, we present a new algorithm m-A*, extending the well-known A* to the m-best task, and for the first time prove that all its desirable properties, including soundness, completeness and optimal efficiency, are maintained. Since bestfirst al...
متن کاملSEARCHING FOR THE M BEST SOLUTIONS IN GRAPHICAL MODELS Searching For The M Best Solutions In Graphical Models
The paper focuses on finding the m best solutions to combinatorial optimization problems using best-first or depth-first branch and bound search. Specifically, we present a new algorithm mA*, extending the well-known A* to them-best task, and for the first time prove that all its desirable properties, including soundness, completeness and optimal efficiency, are maintained. Since bestfirst algo...
متن کاملMethods for advancing combinatorial optimization over graphical models
OF THE DISSERTATION Methods for advancing combinatorial optimization over graphical models By Natalia Flerova Doctor of Philosophy in Computer Science University of California, Irvine, 2015 Rina Dechter, Chair Graphical models are a well-known convenient tool to describe complex interactions between variables. A graphical model defines a function over many variables that factors over an underly...
متن کاملBucket and Mini-bucket Schemes for M Best Solutions over Graphical Models
The paper focuses on the task of generating the first m best solutions for a combinatorial optimization problem defined over a graphical model (e.g., the m most probable explanations for a Bayesian network). We show that the mbest task can be expressed within the unifying framework of semirings making known inference algorithms defined and their correctness and completeness for the m-best task ...
متن کاملSearch Algorithms for m Best Solutions for Graphical Models
The paper focuses on finding the m best solutions to combinatorial optimization problems using Best-First or Branchand-Bound search. Specifically, we present m-A*, extending the well-known A* to the m-best task, and prove that all its desirable properties, including soundness, completeness and optimal efficiency, are maintained. Since Best-First algorithms have memory problems, we also extend t...
متن کامل