Eric Nalisnick - On Prior Specification for Bayesian Neural Networks
|Starts:||14:00 9 Feb 2022|
|Ends:||15:00 9 Feb 2022|
|What is it:||Seminar|
|Organiser:||Department of Mathematics|
|Who is it for:||University staff, External researchers, Current University students|
Eric Nalisnick, Assistant Professor at the Amsterdam Machine Learning Lab, Informatics Institute at the University of Amsterdam is our speaker for the Statistics seminar series.
Title: On Prior Specification for Bayesian Neural Networks
Abstract: Specifying a Bayesian prior is notoriously difficult for complex models such as neural networks. Reasoning about parameters is made challenging by the high-dimensionality and over-parameterization of the space. Priors that seem benign and uninformative can have unintuitive and detrimental effects on a model’s predictions. To help cope with these problems, I will describe our work on predictive complexity priors: a prior that is defined by comparing the model’s predictions to those of a reference model. I will show applications to high-dimensional regression, reasoning over neural network depth, and sharing of statistical strength for few-shot learning.
Organisation: University of Amsterdam
Travel and Contact Information
Zoom link: https://zoom.us/j/92947173491