— In this work, we study the problem of evaluating the performance limit of two communication problems that are closely related to each other- source coding with feed-forward and...
A new training algorithm is presented for delayed reinforcement learning problems that does not assume the existence of a critic model and employs the polytope optimization algorit...
Local features are gaining popularity due to their robustness to occlusion and other variations such as minor deformation. However, using local features for recognition of biometri...
We consider finite horizon Markov decision processes under performance measures that involve both the mean and the variance of the cumulative reward. We show that either randomiz...
A key component of BM25 contributing to its success is its sub-linear term frequency (TF) normalization formula. The scale and shape of this TF normalization component is controll...