With more and more commercial activities moving onto the Internet, people tend to purchase what they need through Internet or conduct some online research before the actual transac...
We present a new online learning algorithm in the selective sampling framework, where labels must be actively queried before they are revealed. We prove bounds on the regret of ou...
To fully tap into the potential of heterogeneous machines composed of multicore processors and multiple accelerators, simple offloading approaches in which the main trunk of the ap...
Many complex, real world phenomena are difficult to study directly using controlled experiments. Instead, the use of computer simulations has become commonplace as a feasible alte...
Online learning algorithms such as Winnow have received much attention in Machine Learning. Their performance degrades only logarithmically with the input dimension, making them us...