The Laboratory for Robust and Efficient Machine Learning

Code for "Multi-Time Attention Networks for Irregularly Sampled Time Series", ICLR 2021.

reml-lab

Heteroscedastic Temporal Variational Autoencoder For Irregularly Sampled Time Series

reml-lab

Codebase for our paper "URSABench: Comprehensive Benchmarking of Approximate Bayesian Inference Methods for Deep Neural Networks"

reml-lab