Inverse molecular design and parameter optimization with Hückel theory using automatic differentiation

Abstract

Semi-empirical quantum chemistry has recently seen a renaissance with applications in high-throughput virtual screening and machine learning. The simplest semi-empirical model still in widespread use in chemistry is Hückel's $\pi$-electron molecular orbital theory. In this work, we implemented a Hückel program using differentiable programming with the JAX framework, based on limited modifications of a pre-existing NumPy version. The auto-differentiable Hückel code enabled efficient gradient-based optimization of model parameters tuned for excitation energies and molecular polarizabilities, respectively, based on as few as 100 data points from density functional theory simulations. In particular, the facile computation of the polarizability, a second-order derivative, via auto-differentiation shows the potential of differentiable programming to bypass the need for numeric differentiation or derivation of analytical expressions. Finally, we employ gradient-based optimization of atom identity for inverse design of organic electronic materials with targeted orbital energy gaps and polarizabilities. Optimized structures are obtained after as little as 15 iterations, using standard gradient-based optimization algorithms.

arXiv comment31 pages, 16 Figures

References in corpus (21)

• Array Programming with NumPy
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Decoupled Weight Decay Regularization
• PennyLane: Automatic differentiation of hybrid quantum-classical computations
• Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics
• Learning the exchange-correlation functional from nature with fully differentiable density functional theory
• Bayesian optimization with known experimental and design constraints for chemistry applications
• Automatic differentiation in quantum chemistry with an application to fully variational Hartree-Fock
• Sample Efficiency Matters: A Benchmark for Practical Molecular Optimization
• DQC: a Python program package for Differentiable Quantum Chemistry
• Deep Molecular Dreaming: Inverse machine learning for de-novo molecular design and interpretability with surjective representations
• Differentiable quantum chemistry with PySCF for molecules and materials at the mean-field level and beyond
• Machine Learned Hückel Theory: Interfacing Physics and Deep Neural Networks
• Efficient and Modular Implicit Differentiation
• Automatic Differentiation for the Direct Minimization Approach to the Hartree-Fock Method
• Arbitrarily Precise Quantum Alchemy
• Excited State Mean-Field Theory without Automatic Differentiation
• Differentiable Physics: A Position Piece
• Inverse design of dissipative quantum steady-states with implicit differentiation
• Automatic differentiation for coupled cluster methods
• Applications of Hückel-Su-Schrieer-Heeger method. I. Carbon-carbon bond lengths in polycyclic aromatic hydrocarbons

Cited by in corpus (6)

• Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science
• Softmax parameterization of the occupation numbers for natural orbital functionals based on electron pairing approaches
• Performant Automatic Differentiation of Local Coupled Cluster Theories: Response Properties and Ab Initio Molecular Dynamics
• MOLPIPx: an end-to-end differentiable package for permutationally invariant polynomials in Python and Rust
• Leveraging Normalizing Flows for Orbital-Free Density Functional Theory
• Algorithmic differentiation for plane-wave DFT: materials design, error control and learning model parameters