REVIEW 24 cited by
A Self-Attention Ansatz for Ab-initio Quantum Chemistry
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
A Self-Attention Ansatz for Ab-initio Quantum Chemistry
read the original abstract
We present a novel neural network architecture using self-attention, the Wavefunction Transformer (Psiformer), which can be used as an approximation (or Ansatz) for solving the many-electron Schr\"odinger equation, the fundamental equation for quantum chemistry and material science. This equation can be solved from first principles, requiring no external training data. In recent years, deep neural networks like the FermiNet and PauliNet have been used to significantly improve the accuracy of these first-principle calculations, but they lack an attention-like mechanism for gating interactions between electrons. Here we show that the Psiformer can be used as a drop-in replacement for these other neural networks, often dramatically improving the accuracy of the calculations. On larger molecules especially, the ground state energy can be improved by dozens of kcal/mol, a qualitative leap over previous methods. This demonstrates that self-attention networks can learn complex quantum mechanical correlations between electrons, and are a promising route to reaching unprecedented accuracy in chemical calculations on larger systems.
Forward citations
Cited by 24 Pith papers
-
Crystallization in the Fractional Quantum Hall Regime with Disorder-Aware Neural Quantum States
Disorder-aware neural quantum states provide the first microscopic evidence for a pinned hole Wigner crystal near ν=2/3 that accounts for reentrant integer quantum Hall physics and reveals an electron-hole asymmetry i...
-
Is Variational Monte Carlo Robust? Sharp Moment Thresholds and Heavy-tailed Stochastic Optimization
VMC local energy and gradient estimators are generically heavy-tailed for common ansatze due to nodal sets, but a new clipped variant converges in the low-moment regime.
-
Is Variational Monte Carlo Robust? Sharp Moment Thresholds and Heavy-tailed Stochastic Optimization
VMC's gradient estimators are generically heavy-tailed (no 3/2 moment for Slater–Jastrow); PS-Clip-VMC, which clips energies and per-sample gradients, is provably convergent under weak moments and stabilizes FermiNet ...
-
Neural-network excited states of $A=4$ nuclei and hypernuclei
First NQS variational Monte Carlo calculation of excited states in A=4 nuclei and hypernuclei, reproducing benchmarks and providing the first ab initio M1 transition strength for ^{4}_ΛH consistent with weak-coupling ...
-
WF-Bench: A Benchmark for Neural Network WaveFunction Expressivity and Scaling Laws
WF-Bench is a new benchmark for neural network wavefunctions that matches them to diverse quantum many-body targets and derives empirical scaling laws for representability based on system size and model parameters lik...
-
Neural network quantum states in the grand canonical ensemble
A new neural quantum state ansatz for bosons in the grand canonical ensemble achieves competitive variational energies in 1D and 2D systems and provides access to one-body reduced density matrices.
-
Fermi Sets: Universal and interpretable neural architectures for fermions
Fermi Sets achieve universal approximation of fermionic wavefunctions using K antisymmetric bases times symmetric neural networks, where K equals 1 in 1D, 2 in 2D, and grows linearly with particle number in higher dimensions.
-
Interpolative Separable Density-Fitting for Transcorrelated Hamiltonians
ISDF compression of transcorrelated integrals enables CCSD-level calculations with near-CBS accuracy on hydrogen chains and benzene up to cc-pCV5Z.
-
Accurate Self-Attention Wavefunctions at Large Scale
Self-attention variational wavefunctions for the 2D homogeneous electron gas up to N=169 yield energies below DMC and a converged collective-mode dispersion including a roton-like minimum.
-
Accurate Self-Attention Wavefunctions at Large Scale
Self-attention neural wavefunctions achieve variational energies below fixed-node DMC for the 2D electron gas at up to 169 particles, recovering collective excitations consistent with the thermodynamic limit.
-
Structured Factorization Approaches for Quantum State Tomography
A unified structured factorization framework for quantum state tomography that parametrizes the density matrix as FF^dagger, supports multiple priors, provides sample complexity bounds, and introduces projected gradie...
-
An Iterative Dual-Channel Neural Quantum State Algorithm for Selected Configuration Interaction
HI-NQS uses a dual-channel autoregressive Transformer NQS inside an iterative sample-diagonalize-update loop to reach chemical accuracy on small molecules and nitrogen active spaces with better determinant scaling than CIPSI.
-
Projected Inverse Iteration: An Eigenvalue Approach to Ground-State Computation with Neural Quantum States
Projected Inverse Iteration reframes ground-state search for neural quantum states as an eigenvalue problem to deliver rapid, spectral-gap-insensitive convergence while retaining polynomial scaling.
-
Scaling Laws for Neural-Network Quantum States
Transformer wave functions for the J1-J2 Heisenberg model exhibit size-independent power-law decay of V-score with compute, with the exponent decreasing as frustration increases.
-
Learning quantum ground states in the space of measurement outcomes
Variational optimization of quantum ground states represented as SIC-POVM outcome probabilities using GRU autoregressive networks, tested on 1D Ising and Heisenberg models up to L=128.
-
Autoregressive One-Step Generative Modeling for Dynamical System Forecasting
MeLISA delivers one-step blockwise generative forecasting for dynamical systems that improves short-term accuracy and long-horizon statistical fidelity over neural operators while matching or exceeding their inference speed.
-
Autoregressive One-Step Generative Modeling for Dynamical System Forecasting
MeLISA extends pixel-space MeanFlow to one-step window-conditioned autoregressive forecasting, improving long-horizon turbulence statistics over neural-operator baselines.
-
Uncovering Exotic Paired States in the 2D Spin-Imbalanced Fermi Gas with Neural Wave Functions
Neural wave functions uncover FFLO, polarized superfluid, phase-separated, and crystalline Cooper-pair phases in the 2D spin-imbalanced Fermi gas.
-
Enhancing Neural-Network Variational Monte Carlo through Basis Transformation
A learnable Gaussian-basis locality parameter α lowers NNVMC variational energies on the 3D electron gas and sharpens the Fermi-liquid–Wigner-crystal transition for message-passing ansatze.
-
Enhancing Neural-Network Variational Monte Carlo through Basis Transformation
A learnable Gaussian basis transformation lowers variational energies in neural-network variational Monte Carlo for the three-dimensional homogeneous electron gas.
-
Large Electron Model: A Universal Ground State Predictor
A parameter-conditioned Fermi Sets neural network, trained by variational Monte Carlo on a small grid of (λ,N), predicts ground-state wavefunctions of 2D quantum dots for unseen interaction strengths and particle numb...
-
Attention is all you need to solve chiral superconductivity
A general-purpose self-attention Fermi neural network finds chiral p_x ± ip_y superconductivity in an attractive Fermi gas via unbiased energy minimization.
-
Neuralized Fermionic Tensor Networks for Quantum Many-Body Systems
NN-fTNS enhance fermionic tensor networks with neural parametrization to improve expressivity and achieve order-of-magnitude better energies than pure fTNS on Hubbard models while maintaining linear scaling.
-
Scaling universal Fermi network toward ground states: A diffusion-Monte-Carlo assessment
By scaling a universal fermionic neural network and certifying it with fixed-phase diffusion Monte Carlo, the paper shows the variational energy descending toward the exact ground state, with the DMC gap collapsing to...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.