Direct/adaptive-mixture phase-gradient learning for neural-network quantum states with complex phase structure

• URL: http://arxiv.org/abs/2606.13912v1
• Date: Thu, 11 Jun 2026 21:05:28 GMT
• Title: Direct/adaptive-mixture phase-gradient learning for neural-network quantum states with complex phase structure
• Abstract summary: Estimator design emerges as a first-class lever for complex neural quantum states.<n>We show how a small network trained this way reaches $0.89%$ median error, where tuned standard baselines plateau at $1.8%$.<n>The advantage carries over to chiral XXX chains: the direct estimator again converges to a markedly lower error than the standard one, across $$ and size.
• Score: 3.1413021865737765
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural-network quantum states (NQS) are a leading variational tool for quantum many-body physics, yet their optimization is fragile whenever the ground state carries a non-trivial sign or complex phase structure, a situation generic to gauge fields, broken time-reversal symmetry, and fermionic statistics. We trace this fragility to the stochastic estimator of the phase gradient rather than to network expressiveness. The phase sector of the Monte Carlo energy gradient is a noisy score-function estimator; differentiating the local energy instead yields a direct estimator that is unbiased for the same phase force, has far lower variance, and requires only a separated amplitude--phase ansatz. Demonstrated on a 100-site flux ladder, a small network trained this way reaches $0.89\%$ median error, where tuned standard baselines plateau at $1.8\%$ and wider or deeper standard-gradient networks degrade from $8.4\%$ to $24.6\%$. The advantage carries over to chiral XXX chains: the direct estimator again converges to a markedly lower error than the standard one, across $α$ and size; it grows with flux and vanishes in zero-flux controls. An adaptive-mixture of the two estimators is provably never worse in variance than the better endpoint at the optimal mixing coefficient, with seed-resolved diagnostics tracing much of the gain to eliminating failed runs. Estimator design thus emerges as a first-class lever for complex-valued neural quantum states.

Related papers

• Kibble-Zurek Dynamics in Two-dimensional Frustrated Systems with a Neural Foundation-state Subspace Method [0.6524460254566904]
  We introduce a Neural Foundation-state Subspace (NFS) method for near-adiabatic dynamics.<n>A foundation neural-network quantum state represents the ground-state manifold along the driving path.<n>We validate the method on the two-dimensional transverse-field Ising model.
  arXiv  Detail & Related papers  (2026-09-03T16:58:54Z)
• Scalable Lindblad Noise Learning via Stochastic Tensor-Network Simulation [48.887627688666974]
  Learning dissipation rates in large-scale open quantum systems is a major obstacle for near-term quantum technologies.<n>Here, we propose a scalable noise-learning framework for Lindblad dissipation rates that combines a simulation method, the Jump Method (TJM)<n>We demonstrate the approach on two noise models in the Ising model, in which independent dissipation rates are learned for each site up to $N_mathrmsite=16$.<n>This combination of scalable numerics and rigorous theoretical guarantees positions TJM-based noise learning as a practical foundation for characterizing dissipation in large quantum devices.
  arXiv  Detail & Related papers  (2026-08-25T15:07:11Z)
• Phasor Attention: Mean Root Square Normalization for Phase Manifold Preservation [3.0459410574367314]
  We introduce Mean Root Square Normalization (MRSNorm)<n>MRSNorm mathematically inverts the traditional scaling paradigm.<n>We analytically demonstrate that this constraint yields a built-in, trigonometric gradient clipper governed by the Pythagorean identity.
  arXiv  Detail & Related papers  (2026-07-20T11:10:51Z)
• Cross-Layer Error Compensation and Finite-Sample Feature-Statistics Matching for Extreme Low-Bit Quantization of Large Language Models [0.0]
  We formulate quantization as a joint optimization over the discrete codes and scales of all layers.<n>We show that error compensation alone reaches a perplexity ratio of 9.56 +/- 0.15 over the FP16 teacher.<n>On Qwen2.5-1.5B with 1.125-bit group-binary weights, error compensation alone reaches a perplexity ratio of 9.56 +/- 0.15 over the FP16 teacher.
  arXiv  Detail & Related papers  (2026-07-16T06:47:52Z)
• Exact Law of Quantum Reversibility under Gaussian Pure Loss [2.0305676256390934]
  We show that the quantum version of this principle obeys an exact law with a sharp phase boundary.<n>For Gaussian pure-loss dynamics, the exact cost is additive in a canonical set of mode-resolved data.<n>These results establish an exact law of quantum reversibility in the canonical pure-loss setting.
  arXiv  Detail & Related papers  (2026-03-19T15:24:06Z)
• Stability and Generalization of Push-Sum Based Decentralized Optimization over Directed Graphs [55.77845440440496]
  Push-based decentralized communication enables optimization over communication networks, where information exchange may be asymmetric.<n>We develop a unified uniform-stability framework for the Gradient Push (SGP) algorithm.<n>A key technical ingredient is an imbalance-aware generalization bound through two quantities.
  arXiv  Detail & Related papers  (2026-02-24T05:32:03Z)
• Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching [60.37045080890305]
  We provide the first analysis of the sample complexity for flow-matching based generative models.<n>We decompose the velocity field estimation error into neural-network approximation error, statistical error due to the finite sample size, and optimization error due to the finite number of optimization steps for estimating the velocity field.
  arXiv  Detail & Related papers  (2025-12-01T05:14:25Z)
• Risk-Entropic Flow Matching [0.0]
  Tilted (entropic) risk, obtained by applying a log-exponential transform to a base loss, is a well established tool in statistics and machine learning.<n>We apply the standard risk-sensitive (log-exponential) transform to the conditional FM loss and show that the resulting tilted risk loss is a natural upper-bound on a meaningful conditional entropic FM objective.
  arXiv  Detail & Related papers  (2025-11-28T00:37:37Z)
• Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations [57.179679246370114]
  We identify the distribution of random perturbations that minimizes the estimator's variance as the perturbation stepsize tends to zero.<n>Our findings reveal that such desired perturbations can align directionally with the true gradient, instead of maintaining a fixed length.
  arXiv  Detail & Related papers  (2025-10-22T19:06:39Z)
• Phase Transitions in Open Dicke Model: a degenerate perturbation theory approach [0.0]
  We study the steady-state behavior of the open Dicke model, which describes the collective interaction of $N$ spin-$1/2$ particles with a lossy, quantized cavity mode.<n>While the standard model conserves total spin, Kirton and Keeling citePhysRevLett.118.123602 demonstrated that even infinitesimal homogeneous local dephasing destroys this phase transition.<n>We analyze this interplay using perturbation theory across subspaces of fixed total spin, $S$.
  arXiv  Detail & Related papers  (2025-05-19T04:33:30Z)
• Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum [78.27945336558987]
  Decentralized server (DFL) eliminates reliance on client-client architecture.<n>Non-smooth regularization is often incorporated into machine learning tasks.<n>We propose a novel novel DNCFL algorithm to solve these problems.
  arXiv  Detail & Related papers  (2025-04-17T08:32:25Z)
• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• Enhanced nonlinear quantum metrology with weakly coupled solitons and particle losses [58.720142291102135]
  We offer an interferometric procedure for phase parameters estimation at the Heisenberg (up to 1/N) and super-Heisenberg scaling levels. The heart of our setup is the novel soliton Josephson Junction (SJJ) system providing the formation of the quantum probe. We illustrate that such states are close to the optimal ones even with moderate losses.
  arXiv  Detail & Related papers  (2021-08-07T09:29:23Z)
• Normalization effects on shallow neural networks and related asymptotic expansions [20.48472873675696]
  In particular, we investigate the effect of different scaling schemes, which lead to different normalizations of the neural network, on the network's statistical output. We develop an expansion for the neural network's statistical output pointwise with respect to the scaling parameter as the number of hidden units grows to infinity. We show that to leading order in $N$, the variance of the neural network's statistical output decays as the implied normalization by the scaling parameter approaches the mean field normalization.
  arXiv  Detail & Related papers  (2020-11-20T16:33:28Z)
• Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment [52.02794488304448]
  We propose a new distribution alignment method based on a log-likelihood ratio statistic and normalizing flows. We experimentally verify that minimizing the resulting objective results in domain alignment that preserves the local structure of input domains.
  arXiv  Detail & Related papers  (2020-03-26T22:10:04Z)

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.