Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.21247 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912474109837312 |
|---|---|
| author | Karandashev, Konstantin |
| author_facet | Karandashev, Konstantin |
| contents | A computationally efficient protocol for machine learning in chemical space using Boltzmann ensembles of conformers as input is proposed; the method is based on rewriting Kernel Ridge Regression expressions in terms of Structured Orthogonal Random Features, yielding physics-motivated trigonometric neural networks. To evaluate the method's utility for materials discovery, we test it on experimental datasets of two quantities related to battery electrolyte design, namely oxidation potentials in acetonitrile and hydration energies, using several popular molecular representations to demonstrate the method's flexibility. Despite only using computationally cheap forcefield calculations for conformer generation, we observe systematic decrease of machine learning error with increased training set size in all cases, with experimental accuracy reached after training on hundreds of molecules and prediction errors being comparable to state-of-the-art machine learning approaches. We also present novel versions of Huber and LogCosh loss functions that made hyperparameter optimization of the new approach more convenient. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_21247 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Kernel Ridge Regression for conformer ensembles made easy with Structured Orthogonal Random Features Karandashev, Konstantin Chemical Physics Computational Physics A computationally efficient protocol for machine learning in chemical space using Boltzmann ensembles of conformers as input is proposed; the method is based on rewriting Kernel Ridge Regression expressions in terms of Structured Orthogonal Random Features, yielding physics-motivated trigonometric neural networks. To evaluate the method's utility for materials discovery, we test it on experimental datasets of two quantities related to battery electrolyte design, namely oxidation potentials in acetonitrile and hydration energies, using several popular molecular representations to demonstrate the method's flexibility. Despite only using computationally cheap forcefield calculations for conformer generation, we observe systematic decrease of machine learning error with increased training set size in all cases, with experimental accuracy reached after training on hundreds of molecules and prediction errors being comparable to state-of-the-art machine learning approaches. We also present novel versions of Huber and LogCosh loss functions that made hyperparameter optimization of the new approach more convenient. |
| title | Kernel Ridge Regression for conformer ensembles made easy with Structured Orthogonal Random Features |
| topic | Chemical Physics Computational Physics |
| url | https://arxiv.org/abs/2505.21247 |