Negative Dependence and Sampling in Machine Learning

Negative Dependence and Sampling in Machine Learning

Neyman Seminar
Sep 27, 2017, 04:00 PM - 05:00 PM | 1011 Evans Hall | Happening As Scheduled
Stefanie Jegelka, Massachusetts Institute of Technology
Discrete Probability distributions with strong negative dependencies (negative association) occur in a wide range of settings in Machine Learning, from probabilistic modeling to randomized algorithms for accelerating a variety of popular ML models. In addition, these distributions enjoy rich theoretical connections and properties. A prominent example are Determinantal Point Processes. In this...