We introduce a novel framework for simultaneous structure and parameter learning in hidden-variable conditional probability models, based on an entropic prior and a solution for i...
We consider the validation of randomly generated patterns in a Monte-Carlo Tree Search program. Our bandit-based genetic programming (BGP) algorithm, with proved mathematical prope...
Quadratic program relaxations are proposed as an alternative to linear program relaxations and tree reweighted belief propagation for the metric labeling or MAP estimation problem...
Abstract. Four local search algorithms are investigated for the phylogenetic tree reconstruction problem under the Maximum Parsimony criterion. A new subtree swapping neighborhood ...
In this paper, we formalize and prove the statement that coincidences cannot be accidental, a statement that underlies many useful heuristics in mathematics and physics. Our proof...