Abstract
DCD-FG (Differentiable Causal Discovery for Factor Graphs) addresses the challenge of learning causal relationships among thousands of variables, a setting that arises naturally in single-cell perturbation experiments. The talk presents the method, its theoretical motivation, and applications to high-dimensional biological data.
Date
Nov 1, 2023
Location
Cambridge, MA, USA
Cambridge, MA, United States
Romain Lopez
Assistant Professor of Computer Science and Biology
My research interests lie at the intersection of statistics, computation and modeling of biological data. A significant part of my research is driven by building more statistically accurate and faster machine learning software for analyzing genomics data.