We cast model-free reinforcement learning as the problem of maximizing the likelihood of a probabilistic mixture model via sampling, addressing both the infinite and finite horizo...
Deep learning has been successfully applied to perform non-linear embedding. In this paper, we present supervised embedding techniques that use a deep network to collapse classes....
Martin Renqiang Min, Laurens van der Maaten, Zinen...
— A key step in many statistical learning methods used in machine learning involves solving a convex optimization problem containing one or more hyper-parameters that must be sel...
Kristin P. Bennett, Jing Hu, Xiaoyun Ji, Gautam Ku...
Prediction is an important task in robot motor control where it is used to gain feedback for a controller. With such a self-generated feedback, which is available before sensor rea...
We propose a novel variant of the conjugate gradient algorithm, Kernel Conjugate Gradient (KCG), designed to speed up learning for kernel machines with differentiable loss functio...