Variational Learning is Effective for Large Deep Networks
Abstract
We give extensive empirical evidence against the common belief that variational learning is ineffective for large neural networks. We show that an optimizer called Improved Variational Online Newton (IVON) consistently matches or outperforms Adam for training large networks such as GPT-2 and ResNets from scratch. IVON's computational costs are nearly identical to Adam but its predictive uncertainty is better. We show several new use cases of IVON where we improve finetuning and model merging in Large Language Models, accurately predict generalization error, and faithfully estimate sensitivity to data. We find overwhelming evidence that variational learning is effective.
Cite
@article{arxiv.2402.17641,
title = {Variational Learning is Effective for Large Deep Networks},
author = {Yuesong Shen and Nico Daheim and Bai Cong and Peter Nickl and Gian Maria Marconi and Clement Bazan and Rio Yokota and Iryna Gurevych and Daniel Cremers and Mohammad Emtiyaz Khan and Thomas Möllenhoff},
journal= {arXiv preprint arXiv:2402.17641},
year = {2024}
}
Comments
Published at International Conference on Machine Learning (ICML), 2024. The first two authors contributed equally. Code is available here: https://github.com/team-approx-bayes/ivon