Hippolyt Ritter

Bayesian Online Meta-Learning with Laplace Approximation.

2020

Neural networks are known to suffer from catastrophic forgetting when trained on sequential datasets. While there have been numerous attempts to solve this problem for large-scale supervised classification, little has been done to overcome catastrophic …

Black-box Coreset Variational Inference

2022 · arXiv (Cornell University)

Recent advances in coreset methods have shown that a selection of representative datapoints can replace massive volumes of data for Bayesian inference, preserving the relevant statistical information and significantly accelerating subsequent downstream tasks. Existing variational …