.png){kind=icon}
Return
Reconstructing Kernel-Based Machine Learning Force Fields with Superlinear Convergence
.png){kind=icon}
OA
AI
DOI：10.1021/acs.jctc.2c01304.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Kernel machines have sustained continuous progress in the field of quantum chemistry. In particular, they have proven to be successful in the low-data regime of force field reconstruction. This is because many equivariances and invariances due to physical symmetries can be incorporated into the kernel function to compensate for much larger data sets. So far, the scalability of kernel machines has however been hindered by its quadratic memory and cubical runtime complexity in the number of training points. While it is known that iterative Krylov subspace solvers can overcome these burdens, their convergence crucially relies on effective preconditioners, which are elusive in practice. Effective preconditioners need to partially presolve the learning problem in a computationally cheap and numerically robust manner. Here, we consider the broad class of Nystro''m-type methods to construct preconditioners based on successively more sophisticated low-rank approximations of the original kernel matrix, each of which provides a different set of computational trade-offs. All considered methods aim to identify a representative subset of inducing (kernel) columns to approximate the dominant kernel spectrum.
Keywords:
CONJUGATE GRADIENTS
GAUSSIAN PROCESS
NYSTROM
MATRIX
APPROXIMATION
ACCURATE
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
5.5
Papers:
1.1W
Citations:
5.4W
Organization
Cited Papers
ShareSaveE(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials.png)
NATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAIShareSaveSpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effectsNATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAIShareSavePancreatic cancer cells can evade immune surveillance via nonfunctional Fas (APO-1/CD95) receptors and aberrant expression of functional Fas ligandSurgery
SurgeryIF0
PREAI
ShareSaveShareSaveShareSaveAccurate interatomic force fields via machine learning with covariant kernelsPHYSICAL REVIEW BOAAI
PHYSICAL REVIEW BIF3.7
OAAIShareSave
ShareSave
View more