Portrait de Khang Ngo

Khang Ngo

Doctorat - McGill
Superviseur⋅e principal⋅e
Siamak Ravanbakhsh
Sujets de recherche
Apprentissage automatique pour les sciences physiques
IA pour la science
Modélisation moléculaire
Google Scholar
GitHub

Publications

Scaling Laws and Symmetry, Evidence from Neural Force Fields
Khang Ngo
Siamak Ravanbakhsh
We present an empirical study in the geometric task of learning interatomic potentials, which shows equivariance matters even more at larger… (voir plus) scales; we show a clear power-law scaling behaviour with respect to data, parameters and compute with ``architecture-dependent exponents''. In particular, we observe that equivariant architectures, which leverage task symmetry, scale better than non-equivariant models. Moreover, among equivariant architectures, higher-order representations translate to better scaling exponents. Our analysis also suggests that for compute-optimal training, the data and model sizes should scale in tandem regardless of the architecture. At a high level, these results suggest that, contrary to common belief, we should not leave it to the model to discover fundamental inductive biases such as symmetry, especially as we scale, because they change the inherent difficulty of the task and its scaling laws.
2025-10-10
ArXiv (prépublication)
arxiv.org
arxiv.org
Scaling Laws and Symmetry, Evidence from Neural Force Fields
Khang Ngo
Siamak Ravanbakhsh
We present an empirical study in the geometric task of learning interatomic potentials, which shows equivariance matters even more at larger… (voir plus) scales; we show a clear power-law scaling behaviour with respect to data, parameters and compute with ``architecture-dependent exponents''. In particular, we observe that equivariant architectures, which leverage task symmetry, scale better than non-equivariant models. Moreover, among equivariant architectures, higher-order representations translate to better scaling exponents. Our analysis also suggests that for compute-optimal training, the data and model sizes should scale in tandem regardless of the architecture. At a high level, these results suggest that, contrary to common belief, we should not leave it to the model to discover fundamental inductive biases such as symmetry, especially as we scale, because they change the inherent difficulty of the task and its scaling laws.
2025-10-10
ArXiv (prépublication)
arxiv.org
arxiv.org