When equipped with kernel functions, online learning algorithms are susceptible to the "curse of kernelization" that causes unbounded growth in the model size. To addres...
Inspired by co-training, many multi-view semi-supervised kernel methods implement the following idea: find a function in each of multiple Reproducing Kernel Hilbert Spaces (RKHSs)...
In this paper we introduce two new methods for solving binary quadratic problems. While spectral relaxation methods have been the workhorse subroutine for a wide variety of comput...
The earth mover's distance (EMD) [16] is an important perceptually meaningful metric for comparing histograms, but it suffers from high (O(N3 log N)) computational complexity...
Within Valiant'smodel of learning as formalized by Kearns, we show that computable total predicates for two formallyuncomputable problems the classical Halting Problem, and t...