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 training.
Convergence analysis of stochastic gradient descent with mcmc estimators
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Convergence holds for momentum μ less than 1 in SPRING under mild assumptions, but μ=1 risks divergence; PRIME-SR adapts momentum via spectral dimension and subspace overlap to match tuned performance with better robustness.
citing papers explorer
-
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 training.
-
Momentum Stability and Adaptive Control in Stochastic Reconfiguration
Convergence holds for momentum μ less than 1 in SPRING under mild assumptions, but μ=1 risks divergence; PRIME-SR adapts momentum via spectral dimension and subspace overlap to match tuned performance with better robustness.