Michal Kucer — accepted AI-conference papers

2025

Posterior Mean Matching: Generative Modeling through Online Bayesian Inference

Sebastian Salazar, Michal Kucer, Yixin Wang, Emily Casleton, David Blei

AISTATS 2025poster

This paper introduces 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 diffu…

Cited by 0 Source ↗Scholar ↗

2022

Robustness to Label Noise Depends on the Shape of the Noise Distribution

Diane Oyen, Michal Kucer, Nick Hengartner, Har Simrat Singh

NeurIPS 2022accept

Machine learning classifiers have been demonstrated, both empirically and theoretically, to be robust to label noise under certain conditions --- notably the typical assumption is that label noise is independent of the features given the class label. We provide a theoretical framework that generaliz…

Cited by 10 Source ↗PDF ↗Scholar ↗