In many applied problems in the context of pattern recognition, the data often involve highly asymmetric observations. Normal mixture models tend to overfit when additional compone...
Classical rate-distortion theory requires knowledge of an elusive source distribution. Instead, we analyze rate-distortion properties of individual objects using the recently devel...
We bound the future loss when predicting any (computably) stochastic sequence online. Solomonoff finitely bounded the total deviation of his universal predictor M from the true d...
Stimulus selectivity of sensory systems is often characterized by analyzing responseconditioned stimulus ensembles. However, in many cases these response-triggered stimulus sets h...
The information outage probability of a shot-noise limited direct detection multiple-input multipleoutput (MIMO) optical channel subject to block fading is considered. Information...