I'm a fifth year PhD student at USC working with Greg Ver Steeg and Aram Galstyan using information theory for unsupervised machine learning. I think a lot about rate-distortion and the Information Bottleneck method. Recently, I've worked on the Thermodynamic Variational Objective and its relationship to information geometry.
Recent Talks: ICML 2020
All in the Exponential FamilyNeurIPS Information Geometry Workshop 2020 (Best Paper Award) AIS with q-Paths