|国家预印本平台
首页|Kernel Ridge Regression for conformer ensembles made easy with Structured Orthogonal Random Features

Kernel Ridge Regression for conformer ensembles made easy with Structured Orthogonal Random Features

Kernel Ridge Regression for conformer ensembles made easy with Structured Orthogonal Random Features

来源:Arxiv_logoArxiv
英文摘要

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. The resulting method is tested on experimental datasets of 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.

Konstantin Karandashev

计算技术、计算机技术化学

Konstantin Karandashev.Kernel Ridge Regression for conformer ensembles made easy with Structured Orthogonal Random Features[EB/OL].(2025-05-27)[2025-06-16].https://arxiv.org/abs/2505.21247.点此复制

评论