← Search

Josef Dean

3 accepted papers

2025

u-$\mu$P: The Unit-Scaled Maximal Update Parametrization

ICLR 2025spotlight

The Maximal Update Parametrization ($\mu$P) aims to make the optimal hyperparameters (HPs) of a model independent of its size, allowing them to be swept using a cheap proxy model rather than the full-size target model. We present a new scheme, u-$\mu$P, which improves upon $\mu$P by combining it wit…

Cited by 7SourcePDFScholar
2024

Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets

ICLR 2024poster

Recently, pre-trained foundation models have enabled significant advancements in multiple fields. In molecular machine learning, however, where datasets are often hand-curated, and hence typically small, the lack of datasets with labeled features, and codebases to manage those datasets, has hindered…

2023

Generating QM1B with PySCF$_{\text{IPU}}$

NeurIPS 2023poster

The emergence of foundation models in Computer Vision and Natural Language Processing have resulted in immense progress on downstream tasks. This progress was enabled by datasets with billions of training examples. Similar benefits are yet to be unlocked for quantum chemistry, where the potential o…

Cited by 0SourcePDFScholar