Date: 2018-11-09

Time: 15:30-16:30

Location: BURN 1104

Abstract:

Density estimation lies at the intersection of statistics, theoretical computer science, and machine learning. We review some old and new results on the sample complexities (also known as minimax convergence rates) of estimating densities of high-dimensional distributions, in particular mixtures of Gaussians and Ising models.

Based on joint work with Hassan Ashtiani, Shai Ben-David, Luc Devroye, Nick Harvey, Christopher Liaw, Yani Plan, and Tommy Reddad.

Speaker

Abbas Mehrabian is an IVADO-Apogée-CFREF Fellow at McGill University working with Luc Devroye and Louigi Addario-Berry. His research focuses on statistics and machine learning theory, e.g., bandit algorithms, density estimation, online learning, randomized algorithms and probabilistic analysis of algorithms

Organized by the McGill Statistics Group

Seminar website: https://mcgillstat.github.io/