Guangming Tan

activity

20222026

most citedFastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs

2 citations · 3 across the 9 of their papers we have counts for

collaborators

Showing 2022Show all

2 papers · 1 filter

physics.comp-ph2022

RLEKF: An Optimizer for Deep Potential with Ab Initio Accuracy

Siyu Hu, Wentao Zhang, Qiuchen Sha +5

It is imperative to accelerate the training of neural network force field such as Deep Potential, which usually requires thousands of images based on first-principles calculation a…

math.NA2022

Backward error analysis of the Lanczos bidiagonalization with reorthogonalization

Haibo Li, Guangming Tan, Tong Zhao

The $k$ -step Lanczos bidiagonalization reduces a matrix $A \in R^{m \times n}$ into a bidiagonal form $B_{k} \in R^{(k + 1) \times k}$ while generates two orthonormal matri…