A Coherence Law for Trainability in Noisy Equivariant Quantum Neural Networks

• URL: http://arxiv.org/abs/2606.30688v1
• Date: Sun, 28 Jun 2026 16:43:36 GMT
• Title: A Coherence Law for Trainability in Noisy Equivariant Quantum Neural Networks
• Abstract summary: We study a quantum neural network structure that does not keep the network trainable once noise is present.<n>We find that two distinct effects govern a trainable gradient.<n>Coherence then determines how fast it decays through the contraction of the off-diagonal sector modes.
• Score: 0.8694591156258423
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Symmetry provides a quantum neural network structure, but on its own it does not keep the network trainable once noise is present. We ask which physical quantity decides whether the gradients of an equivariant circuit survive decoherence, and we answer with a compact training law. Working with U(1)-equivariant brickwork circuits that conserve a charge, we find that two distinct effects govern a trainable gradient. Causality fixes where the gradient can live, confining it to the backward light cone of the readout inside the active charge sector. Coherence then determines how fast it decays through the contraction of the off-diagonal sector modes that the projected readout can actually observe. We prove a light-cone reduction that pins the noiseless gradient to the sector-restricted cone with a lower bound independent of the total qubit number, and we define a readout-visible aligned coherence rate as a Rayleigh quotient of the noise generator along the gradient-carrying mode. A perturbative open-system analysis turns this rate into a leading-order training law. Density-matrix simulations then confirm that the finite-noise degradation follows a single accumulated variable built from noise depth and coherence contraction, with a coefficient of determination of 0.979. The sharpest test comes from a correlated-dephasing channel that has a large worst-case rate but a near-zero aligned rate. The law predicts no gradient loss for this channel, and none is seen. Sector coherence outperforms every standard channel diagnostic we compare it against, and the analysis identifies readout-visible sector coherence as the quantity that links equivariant architecture, open-system dynamics and noisy trainability.

Related papers

• Certifying bipartite entanglement on a superconducting processor from a corrected QAOA cost layer [0.0]
  We report a pre-registered single-device study on the nine-qubit superconducting processor Red at the Barcelona Supercomputing Center.<n>We certify bipartite entanglement of a corrected QAOA cost layer on the good coupler at depth one by two-qubit tomographic negativity.<n>We measure the device physics directly: in a pre-registered manipulation on a fixed Bell preparation, reducing the CZ pulse amplitude causally reduces the certified negativity.
  arXiv  Detail & Related papers  (2026-09-08T22:23:35Z)
• The ZZ feature map induces a signless Laplacian metric: a closed-form classical surrogate for quantum kernel regression [0.0]
  We prove that in the small-bandwidth regime the induced kernel is, to leading order, an anisotropic Gaussian kernel with metric M = I + pi2 Q.<n>The corresponding classical kernel requires no fitted parameters and no quantum simulation.
  arXiv  Detail & Related papers  (2026-08-29T19:59:00Z)
• Quantum Natural Gradient on Quotient Spaces [12.042012916861829]
  Parametrized quantum circuits often contain state-preserving redundancies.<n>We prove that, when the prescribed redundancy exhausts the Fisher kernel, the Moore--Penrose update is the minimum-norm horizontal lift.
  arXiv  Detail & Related papers  (2026-08-29T16:14:16Z)
• The Gain-Engineered Transmon [68.89136228609398]
  We introduce and experimentally realize a noise-biased qubit in a standard transmon-readout resonator circuit.<n>Our results open a path towards using this system as a simple building-block for hardware-efficient quantum error detection and correction schemes.
  arXiv  Detail & Related papers  (2026-08-26T17:00:42Z)
• Intrinsic-Noise Consolidation: A Doob-Barrier-Conditioned Diffusion Turns Analog Device Noise into a Continual-Learning Resource [0.0]
  On analog neuromorphic hardware, intrinsic device noise is normally an accuracy tax.<n>On single-head Split-MNIST (8 seeds) rule lifts retention 10.9 points at an optimum interior.<n>We measure the intrinsic noise on real BrainScaleS-2 (additive, trial-to-trial independent, tunable via on-chip averaging) and run the rule on chip with its noise in the training loop.
  arXiv  Detail & Related papers  (2026-07-08T02:38:02Z)
• Neural Networks as Local-to-Global Computations [0.0]
  We construct a sheaf from any ReLU neural network by encoding each computational step as a restriction map on an edge.<n>Unlike the forward pass, the heat equation propagates information bidirectionally across layers, enabling pinned neurons that impose constraints in both directions.<n>We validate the framework experimentally on small synthetic tasks, confirming the convergence theorems and demonstrating that sheaf-based training, while not yet competitive with gradient descent, obeys quantitative scaling laws predicted by the theory.
  arXiv  Detail & Related papers  (2026-03-16T05:23:31Z)
• On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking [49.1352577985191]
  We present a comprehensive analysis of how two-layer neural networks learn features to solve the modular addition task.<n>Our work provides a full mechanistic interpretation of the learned model and a theoretical explanation of its training dynamics.
  arXiv  Detail & Related papers  (2026-02-18T20:25:13Z)
• Verifying Closed-Loop Contractivity of Learning-Based Controllers via Partitioning [52.23804865017831]
  We address the problem of verifying closed-loop contraction in nonlinear control systems whose controller and contraction metric are both parameterized by neural networks.<n>We derive a tractable and scalable sufficient condition for closed-loop contractivity that reduces to checking that the dominant eigenvalue of a symmetric Metzler matrix is nonpositive.
  arXiv  Detail & Related papers  (2025-12-01T23:06:56Z)
• Switching rates in Kerr resonator with two-photon dissipation and driving [0.0]
  We analytically investigate the switching rate in a two-photon driven Kerr oscillator with finite detuning and two-photon dissipation.<n>Using Kramer's theory together with the $P$-representation, we derive an analytical expression for the bit-flip error rate.
  arXiv  Detail & Related papers  (2025-11-17T12:40:56Z)
• Decentralized Optimization on Compact Submanifolds by Quantized Riemannian Gradient Tracking [45.147301546565316]
  This paper considers the problem of decentralized optimization on compact submanifolds.<n>We propose an algorithm where agents update variables using quantized variables.<n>To the best of our knowledge, this is the first algorithm to achieve an $mathcalO (1/K)$ convergence rate in the presence of quantization.
  arXiv  Detail & Related papers  (2025-06-09T01:57:25Z)
• Enhancing Dispersive Readout of Superconducting Qubits Through Dynamic Control of the Dispersive Shift: Experiment and Theory [47.00474212574662]
  A superconducting qubit is coupled to a large-bandwidth readout resonator. We show a beyond-state-of-the-art two-state-readout error of only 0.25,%$ in 100 ns integration time. The presented results are expected to further boost the performance of new and existing algorithms and protocols.
  arXiv  Detail & Related papers  (2023-07-15T10:30:10Z)
• Learning Discretized Neural Networks under Ricci Flow [48.47315844022283]
  We study Discretized Neural Networks (DNNs) composed of low-precision weights and activations.<n>DNNs suffer from either infinite or zero gradients due to the non-differentiable discrete function during training.
  arXiv  Detail & Related papers  (2023-02-07T10:51:53Z)
• Learning Quantized Neural Nets by Coarse Gradient Method for Non-linear Classification [3.158346511479111]
  We propose a class of STEs with certain monotonicity, and consider their applications to the training of a two-linear-layer network with quantized activation functions. We establish performance guarantees for the proposed STEs by showing that the corresponding coarse gradient methods converge to the global minimum.
  arXiv  Detail & Related papers  (2020-11-23T07:50:09Z)

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.