Interpretability and causality have been acknowledged as key ingredients to the success and evolution of modern machine learning systems. Graphical models, and more specifically directed acyclic graphs (DAGs, also known as Bayesian networks), are an established tool for learning and representing interpretable causal models. Unfortunately, estimating the structure of DAGs …
Zhuoran Yang, Princeton University
We consider matrix and tensor factorization problems where there are unimodal constraints. Such methods find application in a variety of problems such as target localization, environmental monitoring, epidemic detection, and medical diagnosis. We presume that we have incomplete (sparse) and noisy samples of a particular field or image and that …
Direct policy gradient methods for reinforcement learning are a successful approach for a variety of reasons: they are model free, they directly optimize the performance metric of interest, and they allow for richly parameterized policies. Their primary drawback is that, by being local in nature, they fail to adequately explore …
Sketching and random projection methods are a powerful set of techniques to speed up computations in numerical linear algebra, statistics, machine learning, optimization and data science. In this talk, we will discuss some of our works on developing a “big data” asymptotic perspective on sketching in the fundamental problems of …