Active learning of potential-energy surfaces of weakly-bound complexes with regression-tree ensembles

Abstract

Several pool-based active learning algorithms (AL) were employed to model potential energy surfaces (PESs) with a minimum number of electronic structure calculations. Theoretical and empirical results suggest that superior strategies can be obtained by sampling molecular structures corresponding to large uncertainties in their predictions while at the same time not deviating much from the true distribution of the data. To model PESs in an AL framework we propose to use a regression version of stochastic query by forest, a hybrid method that samples points corresponding to large uncertainties while avoiding collecting too many points from sparse regions of space. The algorithm is implemented with decision trees that come with relatively small computational costs. We empirically show that this algorithm requires around half the data to converge to the same accuracy in comparison to the uncertainty-based query-by-committee algorithm. Moreover, the algorithm is fully automatic and does not require any prior knowledge of the PES. Simulations on a 6D PES of \pyrrolew show that $<15000$ configurations are enough to build a PES with a generalization error of 16~\invcm, whereas the final model with around 50\,000 configurations has a generalization error of 11~\invcm.

References in corpus (23)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Less is more: sampling chemical space with active learning
• Active learning of linearly parametrized interatomic potentials
• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
• ANI-1: A data set of 20M off-equilibrium DFT calculations for organic molecules
• Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
• Machine Learning Inter-Atomic Potentials Generation Driven by Active Learning: A Case Study for Amorphous and Liquid Hafnium dioxide
• Structure-based Sampling and Self-correcting Machine Learning for Accurate Calculations of Potential Energy Surfaces and Vibrational Levels
• Automated Fitting of Neural Network Potentials at Coupled Cluster Accuracy: Protonated Water Clusters as Testing Ground
• Efficient non-parametric fitting of potential energy surfaces for polyatomic molecules with Gaussian processes
• Bayesian optimization for the inverse scattering problem in quantum reaction dynamics
• Automatically growing global reactive neural network potential energy surfaces: a trajectory free active learning strategy
• Accurate \textit{ab initio} vibrational energies of methyl chloride
• Permutationally Invariant, Reproducing Kernel-Based Potential Energy Surfaces for Polyatomic Molecules: From Formaldehyde to Acetone
• libact: Pool-based Active Learning in Python
• Gaussian process model of 51-dimensional potential energy surface for protonated imidazole dimer
• Spatial separation of pyrrole and pyrrole-water clusters
• Deep Active Learning: Unified and Principled Method for Query and Training