• Publications
  • Influence
Finding MAPs for Belief Networks is NP-Hard
  • S. E. Shimony
  • Mathematics, Computer Science
  • Artif. Intell.
  • 1 August 1994
TLDR
We show that finding the maximum a-posteriori probability (MAP) instantiation of all the random variables given the evidence is NP-hard for Bayesian belief networks, even if the size of the representation is linear in n. Expand
  • 370
  • 38
  • PDF
On Graphical Modeling of Preference and Importance
TLDR
We extend the CP-nets formalism to handle another class of very natural qualitative statements one often uses in expressing preferences in daily life - statements of relative importance of attributes. Expand
  • 169
  • 32
  • PDF
ICBS: The Improved Conflict-Based Search Algorithm for Multi-Agent Pathfinding
Conflict-Based Search (CBS) and its generalization, Meta-Agent CBS are amongst the strongest newly introduced algorithms for Multi-Agent Path Finding. This paper introduces ICBS, an improved versionExpand
  • 116
  • 15
  • PDF
Cost-Based Abduction and MAP Explanation
TLDR
We introduce cost-based abduction as a minimization problem on a DAG (directed acyclic graph) and prove the equivalence of the problem to the Bayesian network MAP (maximum a posteriori probability) solution of the system. Expand
  • 120
  • 14
Selecting Computations: Theory and Applications
TLDR
We develop a theoretical basis for metalevel decisions in the statistical framework of Bayesian selection problems, arguing (as others have done) that this is more appropriate than the bandit framework. Expand
  • 58
  • 12
  • PDF
Support measures for graph data*
TLDR
This paper examines the requirements for admissibility of a support measure. Expand
  • 42
  • 12
  • PDF
Forward Search Value Iteration for POMDPs
TLDR
We propose a new algorithm, FSVI, that uses the underlying MDP to traverse the belief space towards rewards, finding sequences of useful backups, and show how it scales up better than HSVI. Expand
  • 100
  • 11
  • PDF
Computing frequent graph patterns from semistructured data
TLDR
This paper proposes a new algorithm for mining graph data, based on a novel definition of support. Expand
  • 177
  • 9
MCTS Based on Simple Regret
TLDR
We propose a sampling scheme that is "aware" of VOI, achieving an algorithm that in empirical evaluation outperforms both UCT and the other proposed algorithms. Expand
  • 38
  • 8
  • PDF
A Probabilistic Object-Oriented Data Model
TLDR
We outline an object-oriented data model that describes uncertainty through the use of (Bayesian) probabilities. Expand
  • 32
  • 6
...
1
2
3
4
5
...