← Search

Bai Cong

2 accepted papers

2025

Variational Learning Finds Flatter Solutions at the Edge of Stability

NeurIPS 2025spotlight

Variational Learning (VL) has recently gained popularity for training deep neural networks. Part of its empirical success can be explained by theories such as PAC-Bayes bounds, minimum description length and marginal likelihood, but little has been done to unravel the implicit regularization in play…

Cited by 0SourceScholar
2024

Variational Learning is Effective for Large Deep Networks

ICML 2024spotlight

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…