Momentum Stability and Adaptive Control in Stochastic Reconfiguration

arXiv:2604.1835745.0h-index: 2
Predicted impact top 14% in OC · last 90 daysOriginality Incremental advance
AI Analysis

For practitioners of variational Monte Carlo with neural network wavefunctions, this work provides theoretical understanding and a practical solution to the instability caused by momentum in stochastic reconfiguration optimization.

The paper analyzes the sensitivity of the momentum parameter in SPRING for VMC optimization, proving convergence for μ<1 and divergence for μ=1, and proposes PRIME-SR, a tuning-free adaptive method that matches optimally tuned SPRING's performance with improved robustness.

Variational Monte Carlo (VMC) combined with expressive neural network wavefunctions has become a powerful route to high-accuracy ground-state calculations, yet its practical success hinges on efficient and stable wavefunction optimization. While stochastic reconfiguration (SR) provides a geometry-aware preconditioner motivated by imaginary-time evolution, its Kaczmarz-inspired variant, subsampled projected-increment natural gradient descent (SPRING), achieves state-of-the-art empirical performance. However, the effectiveness of SPRING is highly sensitive to the choice of a momentum-like parameter $μ$. The original sensitivity of $μ$ and the instability observed at $μ=1$, have remained unclear. In this work, we clarify the distinct mechanisms governing the regimes $μ<1$ and $μ=1$. We establish convergence guarantees for $0\leμ<1$ under mild assumptions, and construct counterexamples showing that $μ=1$ can induce divergence via uncontrolled growth along kernel-related directions when the step-size is not summable. Motivated by these theoretical insights and numerical observations, we further propose \textit{Principal Range Informed MomEntum SR} (PRIME-SR), a tuning-free momentum-adaptive SR method based on effective spectral dimension and subspace overlap. PRIME-SR achieves performance comparable to optimally tuned SPRING while significantly improving robustness in VMC optimization.

Foundations

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

Your Notes