Abstract

This talk will introduce posterior mean matching (PMM), a new method for generative modeling that is grounded in Bayesian inference. PMM uses conjugate pairs of distributions to model complex data of various modalities like images and text, offering a flexible alternative to existing methods like diffusion models. PMM models iteratively refine noisy approximations of the target distribution using updates from online Bayesian inference. PMM is flexible because its mechanics are based on general Bayesian models. We demonstrate this flexibility by developing specialized examples: a generative PMM model of real-valued data using the Normal-Normal model, a generative PMM model of count data using a Gamma-Poisson model, and a generative PMM model of discrete data using a Dirichlet-Categorical model. Empirically, PMMs achieve performance that is competitive with generative models for language modeling and image generation.

This is joint work with Sebastian Salazar, Michal Kucer, Emily Casleton, and David Blei.

About the Speaker

Yixin Wang is an assistant professor of statistics at the University of Michigan. She works in the fields of Bayesian statistics, machine learning, and causal inference. Previously, she was a postdoctoral researcher with Professor Michael Jordan at the University of California, Berkeley. She completed her PhD in statistics at Columbia, advised by Professor David Blei, and her undergraduate studies in mathematics and computer science at the Hong Kong University of Science and Technology. Her research has been recognized by the NSF CAREER award, the j-ISBA Blackwell-Rosenbluth Award, ICSA Conference Young Researcher Award, ISBA Savage Award Honorable Mention, ACIC Tom Ten Have Award Honorable Mention, and INFORMS data mining and COPA best paper awards.