1

Viral Evolution and Antibody Escape Mutations using Deep Generative Models
We use the epistemic uncertainty of the VAE decoder to guide the optimization of properties of high-dimensional structured objects (e.g., molecules) in latent space.
Nicole Thadani, Nathan Rollins, Sarah Gurev, Pascal Notin, Yarin Gal, Debora Marks
PDF
Improving black-box optimization in VAE latent space using decoder uncertainty
We use the epistemic uncertainty of the VAE decoder to guide the optimization of properties of high-dimensional structured objects (e.g., molecules) in latent space.
Pascal Notin, José Miguel Hernández-Lobato, Yarin Gal
PDF Cite Code Preprint Proceedings
Improving black-box optimization in VAE latent space using decoder uncertainty
Principled Uncertainty Estimation for High Dimensional Data
We introduce an importance sampling-based estimator to estimate the epistemic uncertainty of deep learning models for high-dimensional discrete datasets.
Pascal Notin, José Miguel Hernández-Lobato, Yarin Gal
PDF Cite