Is Variational Monte Carlo Robust? Sharp Moment Thresholds and Heavy-tailed Stochastic Optimization

• URL: http://arxiv.org/abs/2606.26009v1
• Date: Wed, 24 Jun 2026 16:29:54 GMT
• Title: Is Variational Monte Carlo Robust? Sharp Moment Thresholds and Heavy-tailed Stochastic Optimization
• Abstract summary: Variational Carlo (VMC) is a central algorithm in electronic structure theory.<n>In this work, we show that the resulting optimization problem is intrinsically governed by the nodal geometry of the wave function.<n>We introduce a new robust variant of VMC based on clipping both the local energy and a random variable.
• Score: 3.4519796338615225
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Variational Monte Carlo (VMC) is a central algorithm in electronic structure theory and has gained renewed importance through modern neural-network ansätze such as FermiNet. At its core, VMC seeks ground states by minimizing the Rayleigh quotient by stochastic optimization. In this work, we show that the resulting stochastic optimization problem is intrinsically governed by the nodal geometry of the underlying wave function. More precisely, we establish that properties of the nodal set determine the integrability of the local energy and gradient estimators that drive VMC. For broad and practically relevant ansatz classes, including Slater-Jastrow wave functions with variable-exponent Slater-type orbitals, we prove that these estimators are generically heavy-tailed and fail to admit higher moments. At the same time, for general analytic ansätze, we prove weak moment bounds for the relevant estimators and identify precise low-moment regimes, showing how generic and degenerate nodal structures lead to different integrability thresholds. Building on this analysis, we introduce a new robust variant of VMC $\unicode{x2013}$ coined PS-Clip-VMC $\unicode{x2013}$ which is based on clipping both the local energy and the gradient random variable. We prove that PS-Clip-VMC converges both in expectation and with high probability in the weak moment regime of VMC. Preliminary experiments for training FermiNet on Atoms with up to 18 electrons suggest that PS-Clip-VMC is significantly more robust than standard methods.

Related papers

• The Forgotten History of Wave Function Variance Optimization and its Relevance for Neural-Network VMC [0.0]
  Minimizing variance implicitly assumes a Gaussian local energy distribution.<n>For Coulombic systems, the local energy distribution exhibits $E-4$ power-law tails, causing the Central Limit Theorem to fail for the variance estimator.<n>We benchmark these functionals on $H+$, an exactly solvable system at every internuclear distance.<n>While energy minimization by construction yields the lowest energy, variance minimization is surpassed at every $R$ by alternative functionals.
  arXiv  Detail & Related papers  (2026-09-08T08:53:17Z)
• A Defense of the Quadratic Model [71.57026347416729]
  We stress test the simplest possible model of optimization -- the quadratic model.<n>We show that it can be predictive surprisingly in an LLM setting with 150M parameters and 3B training tokens.
  arXiv  Detail & Related papers  (2026-07-23T18:02:03Z)
• From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime [52.459513910242485]
  We develop a general statistical framework for studying optimal noise-level allocation in diffusion training.<n>We show that the optimized training schedule admits an atomic minimizer, concentrated on finitely many noise levels.<n>We then evaluate the entropic schedule in larger-scale experiments, where full schedule optimization is currently intractable.
  arXiv  Detail & Related papers  (2026-07-10T20:59:06Z)
• Momentum Stability and Adaptive Control in Stochastic Reconfiguration [6.526210062544706]
  Variational Monte Carlo (VMC) combined with expressive neural network wavefunctions has become a powerful route to ground-state calculations.<n>We study efficient and stable wavefunction optimization via high-accuracy divergence via adaptive reconfiguration (SR)<n>We propose PRIME-SR, a tuning-free momentum-adaptive SR method based on effective spectral dimension and subspace overlap.
  arXiv  Detail & Related papers  (2026-04-20T14:49:30Z)
• Removing nodal and support-mismatch pathologies in Variational Monte Carlo via blurred sampling [5.276073131901768]
  Variational Monte Carlo (VMC) is a powerful and fast-growing method for optimizing and evolving parameterized body wave functions.<n>In practice, however, without the backbone of the method can become unstable or biased due to the presence of nodes.<n>We introduce blurred sampling to address these difficulties.
  arXiv  Detail & Related papers  (2026-03-18T18:00:05Z)
• Improved energies and wave function accuracy with Weighted Variational Monte Carlo [7.72430072816717]
  This paper interprets variational Monte Carlo (VMC) as a gradient flow in the space of wave functions, followed by a projection step.<n>From this perspective, arbitrary probability distributions can be used in the projection step, allowing the user to prioritize accuracy in different regions of state space.<n>Compared to traditional VMC, weighted VMC reduces the error in the ground state energy by a factor of 2 and it reduces the errors in the local energies away from the mode by large factors of $102$--$104$.
  arXiv  Detail & Related papers  (2025-06-17T05:51:44Z)
• Scaling of Stochastic Normalizing Flows in $\mathrm{SU}(3)$ lattice gauge theory [44.99833362998488]
  Non-equilibrium Markov Chain Monte Carlo simulations provide a well-understood framework based on Jarzynski's equality to sample from a target probability distribution.<n>Out-of-equilibrium evolutions share the same framework of flow-based approaches and they can be naturally combined into a novel architecture called Normalizing Flows (SNFs)<n>We present the first implementation of SNFs for $mathrmSU(3)$ lattice gauge theory in 4 dimensions, defined by introducing gauge-equivariant layers between out-of-equilibrium Monte Carlo updates.
  arXiv  Detail & Related papers  (2024-11-29T19:01:05Z)
• Wasserstein Quantum Monte Carlo: A Novel Approach for Solving the Quantum Many-Body Schr\"odinger Equation [56.9919517199927]
  "Wasserstein Quantum Monte Carlo" (WQMC) uses the gradient flow induced by the Wasserstein metric, rather than Fisher-Rao metric, and corresponds to transporting the probability mass, rather than teleporting it. We demonstrate empirically that the dynamics of WQMC results in faster convergence to the ground state of molecular systems.
  arXiv  Detail & Related papers  (2023-07-06T17:54:08Z)
• Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice [79.48432795639403]
  Mirror descent value iteration (MDVI) is an abstraction of Kullback-Leibler (KL) and entropy-regularized reinforcement learning (RL) We study MDVI with linear function approximation through its sample complexity required to identify an $varepsilon$-optimal policy. We present Variance-Weighted Least-Squares MDVI, the first theoretical algorithm that achieves nearly minimax optimal sample complexity for infinite-horizon linear MDPs.
  arXiv  Detail & Related papers  (2023-05-22T16:13:05Z)
• Convergence Analysis of Stochastic Gradient Descent with MCMC Estimators [8.493584276672971]
  gradient descent (SGD) and its variants is essential for machine learning. In this paper, we consider the SGD algorithm that employ the Markov Chain Monte Carlo (MCMC) estimator to compute the gradient. It is shown that MCMC-SGD escapes from saddle points and reaches $(epsilon,epsilon1/4)$ approximate second order stationary points.
  arXiv  Detail & Related papers  (2023-03-19T08:29:49Z)
• KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal [70.15267479220691]
  We consider and analyze the sample complexity of model reinforcement learning with a generative variance-free model. Our analysis shows that it is nearly minimax-optimal for finding an $varepsilon$-optimal policy when $varepsilon$ is sufficiently small.
  arXiv  Detail & Related papers  (2022-05-27T19:39:24Z)
• Structured Stochastic Gradient MCMC [20.68905354115655]
  We propose a new non-parametric variational approximation that makes no assumptions about the approximate posterior's functional form. We obtain better predictive likelihoods and larger effective sample sizes than full SGMCMC.
  arXiv  Detail & Related papers  (2021-07-19T17:18:10Z)
• What Are Bayesian Neural Network Posteriors Really Like? [63.950151520585024]
  We show that Hamiltonian Monte Carlo can achieve significant performance gains over standard and deep ensembles. We also show that deep distributions are similarly close to HMC as standard SGLD, and closer than standard variational inference.
  arXiv  Detail & Related papers  (2021-04-29T15:38:46Z)
• Kernel and Rich Regimes in Overparametrized Models [69.40899443842443]
  We show that gradient descent on overparametrized multilayer networks can induce rich implicit biases that are not RKHS norms. We also demonstrate this transition empirically for more complex matrix factorization models and multilayer non-linear networks.
  arXiv  Detail & Related papers  (2020-02-20T15:43:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.