Michael I. Jordan

TL;DR: Lower bounds on minimax risks for distributed statistical estimation under a communication budget are established for several problems, including various types of location models, as well as for parameter estimation in regression models.

TL;DR: In this paper, a communication-efficient surrogate likelihood (CSL) framework for distributed statistical inference problems is presented, which provides a communication efficient surrogate to the global likelihoods.

TL;DR: In this paper, a new discrepancy statistic for measuring differences between two probability distributions based on combining Stein's identity with the reproducing kernel Hilbert space theory is derived, and applied to test how well a probabilistic model fits a set of observations.

TL;DR: In this article, a Bayesian nonparametric approach utilizes a hierarchical Dirichlet process prior to learn an unknown number of persistent, smooth dynamical modes, and additionally employs automatic relevance determination to infer a sparse set of dynamic dependencies allowing to learn SLDS with varying state dimension or switching VAR processes with varying autoregressive order.

TL;DR: This work establishes sharp upper and lower bounds on the convergence rates of statistical estimation procedures in a local privacy framework and exhibits a precise tradeoff between the amount of privacy the data preserves and the utility of any statistical estimator or learning procedure.