Qiang Liu, Department of Computer Science
University of Texas at Austin
As a fundamental technique for approximating and bounding distances between probability measures, Stein’s method has caught the attention in the machine learning community recently; some of the key ideas in Stein’s method have been leveraged and extended for developing practical and efficient computational methods for learning and using large scale, intractable probabilistic models.
We will give an overview of Stein’s method in machine learning, focusing on a computable, kernel-based Stein discrepancy for approximating and evaluating (via goodness-of-fit test) distributions with intractable normalization constants, and a Stein variational gradient descent (SVGD) for finding particle-based approximation to intractable distributions that combines the advantages of Markov chain Monte Carlo (MCMC), variational inference and numerical quadrature methods.
Light refreshments will be available.
Bio: Qiang Liu is an assistant professor of computer science at the University of Texas at Austin. His research interests are in machine learning, approximate inference, reinforcement learning, and deep learning. He is an action editor of Journal of Machine Learning Research (JMLR), and received awards such as NSF career.