Multiple Kernel Learning (MKL) can be formulated as a convex-concave minmax optimization problem, whose saddle point corresponds to the optimal solution to MKL. Most MKL methods e...
Zenglin Xu, Rong Jin, Shenghuo Zhu, Michael R. Lyu...
Assume that two points p and q are given and a finite ordered set of simple polygons, all in the same plane; the basic version of a touring-a-sequence-of-polygons problem (TPP) is...
Because of their simplicity, risk measures are often employed in financial risk evaluations and related decisions. In fact, the risk measure ρ(X) of a random variable X is a rea...
Empirical risk minimization offers well-known learning guarantees when training and test data come from the same domain. In the real world, though, we often wish to adapt a classi...
John Blitzer, Koby Crammer, Alex Kulesza, Fernando...
We develop a family of upper and lower bounds on the worst-case expected KL loss for estimating a discrete distribution on a finite number m of points, given N i.i.d. samples. Our...