Shoot from the HIP: Hessian Interatomic Potentials without derivatives

ICLR 2026 Conference Submission4529 Authors

Keywords: Hessian, Molecules, Atomistic Simulation, Transition States, Machine Learning Force Fields, Machine Learning Interatomic Potentials, Molecular Dynamics

TL;DR: Direct prediction of the Hessian with extended MLIPs, with symmetries, >70x faster and more accurate than autograd Hessians.

Abstract:

Fundamental tasks in computational chemistry, from transition state search to vibrational analysis, rely on molecular Hessians, which are the second derivatives of the potential energy. Yet, Hessians are computationally expensive to calculate and scale poorly with system size, with both quantum mechanical methods and neural networks. In this work, we demonstrate that Hessians can be predicted directly from a deep learning model, without relying on automatic differentiation or finite differences.
We observe that one can construct SE(3)-equivariant, symmetric Hessians from irreducible representations (irrep) features up to degree $l$=2 computed during message passing in graph neural networks.
This makes HIP Hessians one to two orders of magnitude faster, more accurate, more memory efficient, easier to train, and enables more favorable scaling with system size. We validate our predictions across a wide range of downstream tasks, demonstrating consistently superior performance for transition state search, accelerated geometry optimization, zero-point energy corrections, and vibrational analysis benchmarks.
We open-source the HIP codebase and model weights to enable further development of the direct prediction of Hessians.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 4529