Scaling Laws for Neural-Network Quantum States

arXiv:2606.0279434.5
Predicted impact top 66% in DIS-NN · last 90 daysOriginality Incremental advance
AI Analysis

For researchers in quantum many-body physics, this paper introduces a general framework to benchmark variational ansätze using scaling laws, analogous to those in machine learning.

This work establishes scaling laws for neural-network quantum states, showing that the V-score decays as a power law in training compute for transformer wave functions approximating ground states of frustrated Heisenberg models. The power-law exponent decreases with frustration, providing a quantitative measure of representational difficulty.

Scaling laws, the power-law relations between loss, architecture size, and compute observed in modern neural networks, offer a quantitative way to characterize the complexity of a learning problem, with the exponent governing the decay of the loss reflecting how rapidly additional resources translate into improved accuracy, and thus how hard the target is to learn. Whether an analogous framework can characterize the complexity of physical problems remains open. We address this question for Neural-Network Quantum States, a leading variational approach for strongly correlated quantum many-body systems. Using transformer wave functions to approximate ground states of the $J_1$-$J_2$ Heisenberg model on triangular and square lattices with up to $20\times 20$ sites, we find that the $V$-score, a measure of accuracy of a variational state, decays as a power law in training compute. Under an appropriate rescaling of compute, results for different system sizes collapse onto a single curve, analogous to scaling collapse in critical phenomena. The resulting power law is, to a good approximation, independent of the number of sites, showing that the transformer Ansatz is size-consistent for the systems considered. The exponent decreases systematically with frustration, identifying it as a quantitative measure of representational difficulty of the ground state and establishing scaling laws as a general framework for benchmarking variational ansätze.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes