Michael I. Jordan

TL;DR: This work proposes Deep Embedded Validation (DEV), which embeds adapted feature representation into the validation procedure to obtain unbiased estimation of the target risk with bounded variance.

TL;DR: In this paper, the authors apply small-variance asymptotics directly to the posterior in Bayesian nonparametric models and obtain a novel objective function that goes beyond clustering to learn (and penalize new) groupings for which they relax the mutual exclusivity and exhaustivity assumptions of clustering.

TL;DR: The challenges and architectural considerations required to achieve this functionality, including the abilities to span online and offline systems, to adaptively adjust model materialization strategies, and to exploit inherent statistical properties such as model error tolerance, all while operating at "Big Data" scale are described.

TL;DR: This paper derives an efficient algorithm for updating the mixture parameters and applies it to the problem of learning in sigmoid belief networks and demonstrates a systematic improvement over simple mean field theory as the number of mixture components is increased.

TL;DR: This work proves bounds on information-theoretic quantities, including mutual information and Kullback-Leibler divergence, that depend on the privacy guarantees, and provides a treatment of several canonical families of problems: mean estimation, parameter estimation in fixed-design regression, multinomial probability estimation, and nonparametric density estimation.