— We have found a more general formulation of the REINFORCE learning principle which had been proposed by R. J. Williams for the case of artificial neural networks with stochast...
We present a new family of subgradient methods that dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative gradie...
Stochastic orders can be applied to Markov reward models and used to aggregate models, while introducing a bounded error. Aggregation reduces the number of states in a model, miti...
Stochastic process algebras such as PEPA provide ample support for the component-based construction of models. Tools compute the numerical solution of these models; however, the st...
The problem of learning metrics between structured data (strings, trees or graphs) has been the subject of various recent papers. With regard to the specific case of trees, some a...