This paper develops bounds on out-of-sample error rates for support vector machines (SVMs). The bounds are based on the numbers of support vectors in the SVMs rather than on VC di...
We present SpeedBoost, a natural extension of functional gradient descent, for learning anytime predictors, which automatically trade computation time for predictive accuracy by s...
This paper gives some global and uniform convergence estimates for a class of subspace correction (based on space decomposition) iterative methods applied to some unconstrained con...
Subdivision is a convenient tool to construct objective curves and surfaces directly from given scattered points. Stationary p-subdivision schemes are highly efficient in the acqui...
Yi-Kuan Zhang, Ke Lu, Jiangshe Zhang, Xiaopeng Zha...