We show that the relevant information of a supervised learning problem is contained up to negligible error in a finite number of leading kernel PCA components if the kernel matche...
Mikio L. Braun, Joachim M. Buhmann, Klaus-Robert M...
We describe and analyze a simple and effective iterative algorithm for solving the optimization problem cast by Support Vector Machines (SVM). Our method alternates between stocha...
In the multi-armed bandit (MAB) problem there are k distributions associated with the rewards of playing each of k strategies (slot machine arms). The reward distributions are ini...
Graph-based methods form a main category of semisupervised
learning, offering flexibility and easy implementation
in many applications. However, the performance of
these methods...
Wei Liu (Columbia University), Shih-fu Chang (Colu...
Reinforcement Learning methods for controlling stochastic processes typically assume a small and discrete action space. While continuous action spaces are quite common in real-wor...