[Statlist] Reminder -- Joint talk: FDS seminar - Research Seminar on Statistics with David Blei, Columbia University -- ETH Zurich, 27 February 2025

[Kaiser-Heinzmann Susanne]

We are pleased to announce and invite you to the following joint talk in our ETH-FDS Seminar - Research Seminar on Statistics:

„Scaling and Generalizing Approximate Bayesian Inference“
by David Blei, Columbia University

Date and Time: Thursday, 27 February 2025, 16.15 - 17.15 (Zurich)
Place: ETH Zurich, HG D 1.2

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.


Seminar websites: https://math.ethz.ch/sfs/news-and-events/data-science-seminar.html, https://math.ethz.ch/sfs/news-and-events/research-seminar.html



ETH Zürich I Seminar für Statistik I Rämistrasse 101 I 8092 Zürich I Telefon +41 44 632 65 18 I sekretariat at stat.math.ethz.ch