We propose a framework MIC (Multiple Inclusion Criterion) for learning sparse models based on the information theoretic Minimum Description Length (MDL) principle. MIC provides an...
Paramveer S. Dhillon, Dean P. Foster, Lyle H. Unga...
Vectors [Extended Abstract] Pekka Orponen and Satu Elisa Schaeffer Laboratory for Theoretical Computer Science, P.O. Box 5400 FI-02015 TKK Helsinki University of Technology, Finlan...
Abstract. In the context of graph transformation we look at the operation of switching, which can be viewed as an elegant method for realizing global transformations of (group-labe...
Andrzej Ehrenfeucht, Jurriaan Hage, Tero Harju, Gr...
We describe a new theoretical framework for robot-aided training of arm movements. This framework is based on recent studies of motor adaptation in human subjects and on general c...
We propose a new algorithm for learning kernels for variants of the Normalized Cuts (NCuts) objective – i.e., given a set of training examples with known partitions, how should ...