Mitigating Measurement-Induced Training Instability in Hybrid Quantum Neural Networks for Protein Classification

• URL: http://arxiv.org/abs/2606.22551v1
• Date: Sun, 21 Jun 2026 15:10:51 GMT
• Title: Mitigating Measurement-Induced Training Instability in Hybrid Quantum Neural Networks for Protein Classification
• Abstract summary: We introduce a learnable scaling parameter, Quantum Measurement Temperature (QMT), which rescales quantum measurement outputs prior to the loss.<n>QMT acts during training and compensates for the physically imposed bounds on quantum measurement outputs.<n>Results demonstrate that QMT enables stable and reliable training of hybrid QNNs for practical applications.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Hybrid Quantum Neural Network (QNN) classifiers produce logits as expectation values of quantum measurement operators. For standard Pauli measurements, these outputs are intrinsically bounded to the interval [-1,1]. When such bounded logits are used directly with the cross-entropy loss applied to softmax-normalized logits for multi-class classification, the loss function operates in a regime of weak sensitivity to logit differences. As a consequence, parameter gradients are suppressed, leading to unstable optimization in variational quantum classifiers (VQCs). In this work, we identify this effect as measurement-induced logit contraction, a previously uncharacterized source of trainability degradation in hybrid QNNs. To address this limitation, we introduce a learnable scaling parameter, termed Quantum Measurement Temperature (QMT), which rescales quantum measurement outputs prior to the loss. Unlike post-hoc calibration, QMT acts during training and compensates for the physically imposed bounds on quantum measurement outputs. This rescaling increases gradient magnitude and variance, thereby improving loss sensitivity. The proposed mechanism is architecture-agnostic and does not modify the quantum ansatz, circuit depth, or measurement operators. Experiments on fluorescence microscopy images and a six-class variant of Fashion MNIST demonstrate that QMT consistently enhances logit separation, strengthens gradients, stabilizes training across random initializations, and improves classification accuracy, relative to unscaled measurement readouts. These results demonstrate that QMT enables stable and reliable training of hybrid QNNs for practical applications.

Related papers

• Scaling Laws for Hybrid Quantum Neural Networks: Depth, Width, and Quantum-Centric Diagnostics [2.2133667529581933]
  Hybrid quantum neural networks are increasingly explored for classification.<n>It remains unclear how their performance and quantum behavior scale with circuit depth and qubit count.<n>We present a controlled scaling study of hybrid quantum-classical classifiers along two axes.
  arXiv  Detail & Related papers  (2026-04-07T15:44:30Z)
• Continual Quantum Architecture Search with Tensor-Train Encoding: Theory and Applications to Signal Processing [68.35481158940401]
  CL-QAS is a continual quantum architecture search framework.<n>It mitigates challenges of costly encoding amplitude and forgetting in variational quantum circuits.<n>It achieves controllable robustness expressivity, sample-efficient generalization, and smooth convergence without barren plateaus.
  arXiv  Detail & Related papers  (2026-01-10T02:36:03Z)
• Quantum-Enhanced Neural Contextual Bandit Algorithms [50.880384999888044]
  This paper introduces the Quantum Neural Tangent Kernel-Upper Confidence Bound (QNTK-UCB) algorithm.<n>QNTK-UCB is a novel algorithm that leverages the Quantum Neural Tangent Kernel (QNTK) to address these limitations.
  arXiv  Detail & Related papers  (2026-01-06T09:58:14Z)
• Calibration of Quantum Devices via Robust Statistical Methods [45.464983015777314]
  We numerically analyze advanced statistical methods for Bayesian inference against the state-of-the-art in quantum parameter learning.<n>We show advantages of these approaches over existing ones, namely under multi-modality and high dimensionality.<n>Our findings have applications in challenging quantumcharacterization tasks namely learning the dynamics of open quantum systems.
  arXiv  Detail & Related papers  (2025-07-09T15:22:17Z)
• Adaptive variational quantum dynamics simulations with compressed circuits and fewer measurements [4.2643127089535104]
  We show an improved version of the adaptive variational quantum dynamics simulation (AVQDS) method, which we call AVQDS(T)<n>The algorithm adaptively adds layers of disjoint unitary gates to the ansatz circuit so as to keep the McLachlan distance, a measure of the accuracy of the variational dynamics, below a fixed threshold.<n>We also show a method based on eigenvalue truncation to solve the linear equations of motion for the variational parameters with enhanced noise resilience.
  arXiv  Detail & Related papers  (2024-08-13T02:56:43Z)
• Trade-off between Gradient Measurement Efficiency and Expressivity in Deep Quantum Neural Networks [0.0]
  Quantum neural networks (QNNs) require an efficient training algorithm to achieve practical quantum advantages.<n>We propose a general QNN ansatz called the stabilizer-logical product ansatz (SLPA), which achieves the trade-off upper bound by exploiting the symmetric structure of the quantum circuit.<n> Numerical experiments show that the SLPA drastically reduces the sample complexity needed for training while maintaining accuracy and trainability.
  arXiv  Detail & Related papers  (2024-06-26T12:59:37Z)
• Analytical and experimental study of center line miscalibrations in M\o lmer-S\o rensen gates [51.93099889384597]
  We study a systematic perturbative expansion in miscalibrated parameters of the Molmer-Sorensen entangling gate. We compute the gate evolution operator which allows us to obtain relevant key properties. We verify the predictions from our model by benchmarking them against measurements in a trapped-ion quantum processor.
  arXiv  Detail & Related papers  (2021-12-10T10:56:16Z)
• Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition [67.95996816744251]
  State-of-the-art language models (LMs) represented by long-short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming increasingly complex and expensive for practical applications. Current quantization methods are based on uniform precision and fail to account for the varying performance sensitivity at different parts of LMs to quantization errors. Novel mixed precision neural network LM quantization methods are proposed in this paper.
  arXiv  Detail & Related papers  (2021-11-29T12:24:02Z)
• 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)
• Improving the accuracy and efficiency of quantum connected moments expansions [4.9834612867114965]
  In quantum chemistry, the variational quantum eigensolver (VQE) algorithm has become ubiquitous. Here we use the ADAPT-VQE algorithm to test shallow circuit construction strategies.
  arXiv  Detail & Related papers  (2021-03-16T15:13:40Z)
• Benchmarking adaptive variational quantum eigensolvers [63.277656713454284]
  We benchmark the accuracy of VQE and ADAPT-VQE to calculate the electronic ground states and potential energy curves. We find both methods provide good estimates of the energy and ground state. gradient-based optimization is more economical and delivers superior performance than analogous simulations carried out with gradient-frees.
  arXiv  Detail & Related papers  (2020-11-02T19:52:04Z)

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.