Timezone: »

A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions
Jayadev Acharya · Hirakendu Das · Alon Orlitsky · Ananda Suresh

Mon Aug 07 11:06 PM -- 11:24 PM (PDT) @ C4.8

Symmetric distribution properties such as support size, support coverage, entropy, and proximity to uniformity, arise in many applications. Recently, researchers applied different estimators and analysis tools to derive asymptotically sample-optimal approximations for each of these properties. We show that a single, simple, plug-in estimator---\emph{profile maximum likelihood (PML)}--is sample competitive for all symmetric properties, and in particular is asymptotically sample-optimal for all the above properties.

Author Information

Jayadev Acharya (Cornell University)
Hirakendu Das (Yahoo!)
Alon Orlitsky (UCSD)
Ananda Suresh (Google)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors