Theory of latent feature learning

Paul Kishan Rubenstein (Ph.D. Student)

Low dimensional, abstract or otherwise 'simple' structure occurs widely across machine learning. This project advances theoretical understanding in a variety of areas. These are: causality, in which a theory of micro-macro abstractions is developed; independent component analysis, in which new identifiability results are derived in a multi-view setting; and generative modelling, where the estimation of divergences in latent spaces is analysed in a learning theoretic framework.

Primary Host:	Bernhard Schölkopf (ELLIS Institute Tübingen & Max Planck Institute for Intelligent Systems)
Exchange Host:	Carl Edward Rasmussen (University of Cambridge)
PhD Duration:	01 October 2015 - 30 June 2020
Exchange Duration:	01 October 2015 - 30 September 2016 - Ongoing