A Statistical Learning Theory Framework for Supervised Pattern Discovery [chapter]

Jonathan H. Huggins, Cynthia Rudin
2014 Proceedings of the 2014 SIAM International Conference on Data Mining  
This paper formalizes a latent variable inference problem we call supervised pattern discovery, the goal of which is to find sets of observations that belong to a single "pattern." We discuss two versions of the problem and prove uniform risk bounds for both. In the first version, collections of patterns can be generated in an arbitrary manner and the data consist of multiple labeled collections. In the second version, the patterns are assumed to be generated independently by identically
more » ... uted processes. These processes are allowed to take an arbitrary form, so observations within a pattern are not in general independent of each other. The bounds for the second version of the problem are stated in terms of a new complexity measure, the quasi-Rademacher complexity. * MIT Department of EECS and CSAIL (jhuggins@mit.edu) † MIT Sloan School of Management and CSAIL (rudin@mit.edu) 1 Ideas from perceptual organization have proven to be very useful in the field of computer vision [20] .
doi:10.1137/1.9781611973440.58 dblp:conf/sdm/HugginsR14 fatcat:ok5bn3jrgjhfrdy6cn6qnxeoci