NucleoNet: A Nuclear-Aware Determinant Ansatz for Multi-Geometry Neural Variational Monte Carlo
We introduce NucleoNet, a nuclear-aware determinant ansatz in which electrons and nuclei form a unified particle set propagated through a shared electron--nucleus backbone that jointly evolves one-particle and two-particle representations.
ProofPaper ↗
Key points
- Neural-network variational Monte Carlo provides an accurate route to solving the electronic Schrödinger equation, but many neural wavefunctions are optimized for a single nuclear geometry, requiring separate calculations to map out a potential energy surface.
- On equilibrium small-molecule benchmarks, NucleoNet achieves accuracy comparable to established neural-wavefunction baselines with substantially fewer parameters.
- For each molecular system, a single model optimized jointly across geometries describes the N$2$ dissociation curve, Li displacement in LiCN, and the ethane and formamide minimum-energy paths for bond dissociation.
- These results show that a compact wavefunction with jointly evolved nuclear representations can describe the geometries of a molecular system with a single set of parameters.
Sources (1)
- [1]NucleoNet: A Nuclear-Aware Determinant Ansatz for Multi-Geometry Neural Variational Monte CarloarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 04:36 AM
We introduce NucleoNet, a nuclear-aware determinant ansatz in which electrons and nuclei form a unified particle set propagated through a shared electron--nucleus backbone that jointly evolves one-particle and two-particle representations.
Neural-network variational Monte Carlo provides an accurate route to solving the electronic Schrödinger equation, but many neural wavefunctions are optimized for a single nuclear geometry, requiring separate calculations to map out a potential energy surface.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 9, 2026Spatial Prediction with Guided Diffusion
- Oct 9, 2026Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training
- Oct 9, 2026Localized Generative Design of Ship Hulls with Diffusion Models and High-Fidelity Assessment
- Oct 9, 2026Robust Langevin Sampling under State-Dependent Heavy-Tailed Noise with Applications to LLM Fine-Tuning
- Oct 8, 2026Distributionally Robust Adaptive Iterative Covariance Steering for Small-Body Proximity Operations
- Oct 7, 2026A Closed-Loop Non-Asymptotic Convergence Analysis of PPO with Learned Critics and Clipping