麻豆AV

Learning Causal Structures via Continuous Optimization

听

There has been a recent surge of interest in the machine learning community in developing causal models that handle the effect of interventions in a system. In this talk, I will consider the problem of learning (estimating) a causal graphical model from data. The search over possible directed acyclic graphs modeling the causal structure is inherently combinatorial, but I鈥檒l describe our recent work which use gradient-based continuous optimization for learning both the parameters of the distribution and the causal graph jointly, and can be combined naturally with flexible parametric families that use neural networks.

Based on joint work with S茅bastien Lachapelle, Philippe Brouillard, R茅mi Le Priol, Reza Babanezhad, Alexandre Drouin, Alexandre Lacoste and Yoshua Bengio.

Simon Lacoste-Julien is an associate professor in the department of computer science and operations research at Universit茅 de Montreal, a co-founding member of Mila, and the part-time director of the SAIT AI Lab Montreal from Samsung. He received the B.Sc. degree in mathematics, physics and computer science from 麻豆AV, and the PhD degree in computer science from University of California, Berkeley, in 2009. Before joining Universit茅 de Montr茅al, he completed a post-doctoral fellowship at University of Cambridge as well as at Inria Paris, and was an Inria researcher in the Department of Computer Science at the Ecole Normale Superieure (ENS) in Paris. His research interests are in machine learning, optimization and statistics with applications to computer vision and natural language processing. He has published more than 50 scientific publications in machine learning, has served as an area chair for all the major machine learning or vision conferences and is an associate editor for TPAMI and JMLR. He received a Google Focused Research Award in 2016 and a CIFAR AI Chair in 2018.

Meeting ID: 843 0865 5572

Passcode: 690084

听