Search

Talk

Data-Driven Priors for Trustworthy Machine Learning

  • Tim Rudner (New York University)
Live Stream

Abstract

Machine learning models, while effective in controlled environments, can fail catastrophically when exposed to unexpected conditions upon deployment. This lack of robustness, well-documented even in state-of-the-art models, can lead to severe harm in high-stakes, safety-critical application domains such as healthcare. This shortcoming raises a central question: How can we develop machine learning models we can trust?

In this talk, I will approach this question from a probabilistic perspective and address deficiencies in the trustworthiness of neural network models using Bayesian principles. Specifically, I will show how to improve the reliability and fairness of neural networks with data-driven domain-informed prior distributions over model parameters. To do so, I will first demonstrate how to perform training in neural networks with such priors using a simple variational optimization objective with a regularizer that reflects the constraints implicitly encoded in the prior. This regularizer is mathematically simple, easy to implement, and can be used as a drop-in replacement for existing regularizers when performing supervised learning in neural networks of any size. I will then show how to construct and use domain-informed data-driven priors to improve uncertainty quantification and group robustness in neural network models for selected application domains.

seminar
30.05.24 13.06.24

Math Machine Learning seminar MPI MIS + UCLA

MPI for Mathematics in the Sciences Live Stream

Katharina Matschke

MPI for Mathematics in the Sciences Contact via Mail

Upcoming Events of this Seminar