Samuel Mueller | "PFNs: Use neural networks for 100x faster Bayesian predictions"

Title: Prior-data Fitted Networks (PFNs): Use neural networks for 100x faster Bayesian predictions
Bayesian methods can be expensive and complicated to approximate with e.g. MCMC or VI. PFNs are a new, cheap and simple method to accurately approximate Bayesian predictions. I will explain how to build a PFN out of a Transformer by meta-learning on artificial data. I present the results from our paper that introduces PFNs (https://arxiv.org/pdf/2112.10510.pdf), in which PFNs beat VI and MCMC for some standard tasks, and a to-be-released follow-up work on Tabular classification, where we show that a simple PFN can replace a full AutoML tool in some scenarios.

Paper: https://arxiv.org/pdf/2112.10510.pdf

Speaker: https://samuelgabriel.github.io/index...