Boosting methods are known to exhibit noticeable overfitting on some datasets, while being immune to overfitting on other ones. In this paper we show that standard boosting algorit...
Abstract. We present an implementation of model-based online reinforcement learning (RL) for continuous domains with deterministic transitions that is specifically designed to achi...
We show that it is possible to use data compression on independently obtained hypotheses from various tasks to algorithmically provide guarantees that the tasks are sufficiently r...
We propose a novel way to induce a random field from an energy function on discrete labels. It amounts to locally injecting noise to the energy potentials, followed by finding t...
Many network applications have stringent end-to-end latency requirements, including VoIP and interactive video conferencing, automated trading, and high-performance computing—wh...
Ramana Rao Kompella, Kirill Levchenko, Alex C. Sno...