We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process (  ¢¡¤£¦¥§ ), and focus on gradient ascent approache...
We consider the estimation of a sparse parameter vector from measurements corrupted by white Gaussian noise. Our focus is on unbiased estimation as a setting under which the difï¬...
Alexander Jung, Zvika Ben-Haim, Franz Hlawatsch, Y...
The problem of finding heavy hitters and approximating the frequencies of items is at the heart of many problems in data stream analysis. It has been observed that several propose...
Radu Berinde, Graham Cormode, Piotr Indyk, Martin ...
We study sparse principal components analysis in the high-dimensional setting, where p (the number of variables) can be much larger than n (the number of observations). We prove o...
Abstract. We show several PAC-style concentration bounds for learning unigrams language model. One interesting quantity is the probability of all words appearing exactly k times in...