Explore a 37-minute lecture by Cynthia Rush from Columbia University on the robustness of α-posteriors and their variational approximations when faced with misspecification. Delve into information-theoretic methods for trustworthy machine learning as part of the Simons Institute series. Gain insights into the challenges and solutions surrounding model misspecification in Bayesian inference and variational approximations, enhancing your understanding of robust machine learning techniques.
On the Robustness to Misspecification of α-Posteriors and Their Variational Approximations
Overview
Syllabus
On the Robustness to Misspecification of α-Posteriors and Their Variational Approximations
Taught by
Simons Institute
Related Courses
-
Introduction to Scientific Machine Learning
-
Variational Approximations for Bayesian and Semi-Bayesian Inferences
-
Concentration of Tempered Posteriors and of Their Variational Approximations – Pierre Alquier
-
Variational Inference for Fun and Profit
-
Variational Inference and Optimization - Lecture 3
-
Robust and Sample-Efficient Simulation-Based Inference
