-- We characterize the best achievable performance of lossy compression algorithms operating on arbitrary random sources, and with respect to general distortion measures. Direct an...
The goal of natural image denoising is to estimate a clean version of a given noisy image, utilizing prior knowledge on the statistics of natural images. The problem has been stud...
The conditional distribution of a discrete variable y, given another discrete variable x, is often specified by assigning one multinomial distribution to each state of x. The cost...
We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...
Current trends in model construction in the field of agentbased computational economics base behavior of agents on either game theoretic procedures (e.g. belief learning, fictit...