USI - Email

Archive / INF Seminars / INF_2025_07_16_David_Blei

USI - Email

	Scaling and Generalizing Approximate Bayesian Inference

Host: Prof. Antonietta Mira

Wednesday

16.07

USI Lugano Campus Est, room D1.15 or online

11:30 - 13:30


	David Blei Columbia University

Biography:

David Blei is a Professor of Statistics and Computer Science at Columbia University, and a member of the Columbia Data Science Institute. He studies probabilistic machine learning, including its theory, algorithms, and application. David has received several awards for his research. He received a Sloan Fellowship (2010), Office of Naval Research Young Investigator Award (2011), Presidential Early Career Award for Scientists and Engineers (2011), Blavatnik Faculty Award (2013), ACM-Infosys Foundation Award (2013), a Guggenheim fellowship (2017), a Simons Investigator Award (2019), and a Lenfest Distinguished Faculty Award (2024). He was the co-editor-in-chief of the Journal of Machine Learning Research from 2018-2023. He is a fellow of the ACM and the IMS.

Abstract: A core problem in statistics and machine learning is to approximate difficult-to-compute probability distributions. This problem is especially important in Bayesian statistics, which frames all inference about unknown quantities as a calculation about a conditional distribution. In this talk I review and discuss innovations in variational inference (VI), a method that approximates probability distributions through optimization. VI has been used in myriad applications in machine learning and Bayesian statistics.
After quickly reviewing the basics, I will discuss two lines of research in VI. I first describe stochastic variational inference, an approximate inference algorithm for handling massive datasets, and demonstrate its application to probabilistic topic models of millions of articles. Then I discuss black box variational inference, a more generic algorithm for approximating the posterior. Black box inference applies to many models but requires minimal mathematical work to implement. I will demonstrate black box inference on deep exponential families---a method for Bayesian deep learning---and describe how it enables powerful tools for probabilistic programming.
Finally, I will highlight some more recent results in variational inference, including statistical theory, score-based objective functions, and interpolating between mean-field and fully dependent variational families.

To join online click here.