We consider the problem of decision-making with side information and unbounded loss functions. Inspired by probably approximately correct learning model, we use a slightly different model that incorporates the notion of side information in a more generic form to make it applicable to a broader class of applications including parameter estimation and system identification. We address sufficient ...

According to the C/D model, the base function for each utterance comprises a skeletal structure represented by a syllable-boundary pulse train and melodic control functions that are linked to individual syllables. The melody includes vocalic, tonal, and some other control variables. The concept of prosody may be generalized to include all base function aspects according to this concept. Melodic...

For the past few lectures we have been discussing online classification in scenarios in which there is a perfect target function. In this lecture we study a more general learning framework, learning from expert advice, which removes the assumption of a perfect target and applies to a wide range of problems beyond just classification. Suppose that you are interested in making a sequence of decis...

‎consider an estimation problem in a one-parameter non-regular distribution when both endpoints of the support depend on a single parameter‎. ‎in this paper‎, ‎we give sufficient conditions for a generalized bayes estimator of a parametric function to be admissible‎. ‎some examples are given‎. ‎