This paper presents an experimental and analytical study of value prediction and its impact on speculative execution in superscalar microprocessors. Value prediction is a new para...
In logic metaprogramming, programs are not stored as plain textfiles but rather derived from a deductive database. While the benefits of this approach for metaprogramming are ob...
To find the best lattice model representation of a given full atom protein structure is a hard computational problem. Several greedy methods have been suggested where results are ...
The UCT algorithm learns a value function online using sample-based search. The TD() algorithm can learn a value function offline for the on-policy distribution. We consider three...
A broad class of boosting algorithms can be interpreted as performing coordinate-wise gradient descent to minimize some potential function of the margins of a data set. This class...