Weighted A* Algorithms for Unsupervised Feature Selection with Provable Bounds on Suboptimality
Arai, Hiromasa (The University of Texas at Dallas) | Xu, Ke (The University of Texas at Dallas) | Maung, Crystal (The University of Texas at Dallas) | Schweitzer, Haim (The University of Texas at Dallas)
Identifying a small number of features that can represent the data is believed to be NP-hard. Previous approaches exploit algebraic structure and use randomization. We propose an algorithm based on ideas similar to the Weighted A* algorithm in heuristic search. Our experiments show this new algorithm to be more accurate than the current state of the art.
Apr-19-2016