Jonathan Lu will present his MSE thesis talk on Friday, April 12, 2019 at 11am in CS 302. The members of his committee are Barbara Engelhardt (advisor) and Ben Raphael (reader). Everyone is invited to attend his talk. His talk title and abstract follows below. Title: Regularized Causal Network Inference from Gaussian Process Time Series Abstract: Many methods have been developed to infer causal networks from time series data, but are often insufficient for modern challenges, such as unevenly spaced time series and hundreds to thousands of possible causal variables. For example, single-cell genomics data consists of thousands of protein-coding genes, whose "pseudotime" trajectories are indexed continuously at varying intervals. Here we develop EncoreGP, a causal network inference method that uses Elastic net regression to discover causal relations between continuous time series trajectories (Gaussian Processes). EncoreGP uses impulse functions as causal kernels to bypass previous assumptions of equal timepoint spacing and discrete effects. It uses elastic net regularization to discover sparse, interpretable networks from high-dimensional data. We validate on multiple benchmark networks for bulk and single-cell genomics. While genomics is our focus, EncoreGP can be applied for causal network inference from any large set of time series with uneven timepoints.