Accelerating Moment Tensor Potentials through post-training pruning

Moment Tensor Potentials (MTPs) are machine-learning interatomic potentials whose basis functions are typically selected using a level-based scheme that is data-agnostic. We introduce a post-training, cost-aware pruning strategy that removes expensive basis functions with minimal loss of accuracy. Applied to nickel and silicon-oxygen systems, it yields models up to seven times faster than standard MTPs. The method requires no new data and remains fully compatible with current MTP implementations