Gaussian processes provide a framework for nonlinear nonparametric Bayesian inference
widely applicable across science and engineering. Unfortunately, their computational …

Classification has become an important task for automatically categorizing documents
based on their respective group. The purpose of classification is to assign the pre-specified …

Online convex optimization (OCO) encapsulates supervised learning when training sets are
large-scale or dynamic, and has grown essential as data has proliferated. OCO decomposes …

A major factor in the success of deep neural networks is the use of sophisticated
architectures rather than the classical multilayer perceptron (MLP). Residual networks …

Reinforcement learning consists of finding policies that maximize an expected cumulative
long-term reward in a Markov decision process with unknown transition probabilities and …

We consider the problem of stochastic optimization with nonlinear constraints, where the
decision variable is not vector-valued but instead a function belonging to a reproducing …

The goal of nonparametric regression is to recover an underlying regression function from
noisy observations, under the assumption that the regression function belongs to a …

In this paper, we study the mistake bound of online kernel learning on a budget. We propose
a new budgeted online kernel learning model, called Ahpatron, which significantly improves …

We consider policy evaluation in infinite-horizon discounted Markov decision problems with
continuous compact state and action spaces. We reformulate this task as a compositional …

Batch training of machine learning models based on neural networks is well established,
whereas, to date, streaming methods are largely based on linear models. To go beyond …