activity
20212026
most citedLow-rank matrix and tensor approximations for compression of machine-learning interatomic potentials

3 citations · 3 across the 4 of their papers we have counts for

collaborators
Showing cond-mat.mtrl-sciShow all

1 paper · 1 filter

cond-mat.mtrl-sci2026

Compressed magnetic Moment Tensor Potentials via low-rank matrix and tensor factorizations

Alexey S. Kotykhov, Alexander V. Shapeev, Maxim Rakhuba +1

We propose a parameter-reduced version of magnetic Moment Tensor Potential (mMTP) based on various matrix and tensor decompositions. The resulting compressed magnetic machine-learn…