← Search

Jonathan Craig Mitchell

2 accepted papers

2022

Learning Probabilistic Models from Generator Latent Spaces with Hat EBM

NeurIPS 2022accept

This work proposes a method for using any generator network as the foundation of an Energy-Based Model (EBM). Our formulation posits that observed images are the sum of unobserved latent variables passed through the generator network and a residual random variable that spans the gap between the gene…

2021

Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based Models

ICLR 2021poster

The vulnerability of deep networks to adversarial attacks is a central problem for deep learning from the perspective of both cognition and security. The current most successful defense method is to train a classifier using adversarial images created during learning. Another defense approach involve…