PAC-Bayes Learning of Conjunctions and Classification of Gene-Expression Data

We propose a "soft greedy" learning algorithm for building small conjunctions of simple threshold functions, called rays, defined on single real-valued attributes. We also propose a PAC-Bayes risk bound which is minimized for classifiers achieving a non-trivial tradeoff between sparsity (the number of rays used) and the magnitude of the separating margin of each ray. Finally, we test the soft greedy algorithm on four DNA micro-array data sets.

• Type: Conference
• Year: 2004
• Where: NIPS
• Authors: Mario Marchand, Mohak Shah
• Keywords: NIPS 2004, NIPS 2007, Simple Threshold Functions, Single Real-valued Attributes, Soft Greedy Algorithm