Impact of Data Loss in Postprocessing on Training and Inference of Quantum Neural Networks

• URL: http://arxiv.org/abs/2609.05060v1
• Date: Fri, 04 Sep 2026 12:22:13 GMT
• Title: Impact of Data Loss in Postprocessing on Training and Inference of Quantum Neural Networks
• Abstract summary: Postprocessing routines encode assumptions that no longer hold on utility-scale devices.<n>We present a case study of textttSamplerQNN, the sampling-based quantum neural network class in the Qiskit Machine Learning library.<n>On our quantum hardware runs, where bit-strings span over 100 physical qubits, this filter led to the loss of 85 to 99.6% of valid measurement shots.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As quantum hardware scales to larger devices, the classical software layers that interface with it must evolve in step. Postprocessing routines developed and tested primarily in simulator settings can encode assumptions that no longer hold on utility-scale devices, leading to data loss that can be difficult to detect from high-level model outputs alone. We present a case study of \texttt{SamplerQNN}, the sampling-based quantum neural network class in the Qiskit Machine Learning library. Here, the postprocessing method applies a filter that assumes measurement bit-strings are in virtual qubit space. On our quantum hardware runs, where bit-strings span over 100 physical qubits, this filter led to the loss of 85 to 99.6\% of valid measurement shots, depending on the transpiler's qubit placement. The resulting probability vector is unnormalised, allowing distorted prediction and loss values to propagate through the model without an API-level warning. We demonstrate the impact across five experiments on two IBM backends: for inference, accuracy drops from 0.94 to 0.39 on the same raw measurements; for training, the loss signal is compressed by 22 to 27$\times$, substantially reducing the sensitivity of the optimiser to the objective landscape. The behaviour arises in all released versions of the library (0.8.4 to 0.9.0). We implemented a layout-based marginalisation fix, merged into the GitHub codebase as Pull Request \#1041, that makes \texttt{SamplerQNN} postprocessing forward-compatible with current and upcoming hardware.

Related papers

• Dissipatively Stabilized 0-n Fock Qubits for Noise-Biased Quantum Computing [0.027998963147546147]
  Noise-biased qubits have bit-flip errors that are exponentially suppressed relative to phase-flip errors.<n>We propose a "0-n" Fock qubit architecture that maintains the noise bias by encoding information in the ground state.<n>We numerically demonstrate that bit-flip probabilities approaching $10-8$ are achievable for controlled-X gates on cat qubits.
  arXiv  Detail & Related papers  (2026-08-26T16:20:43Z)
• Latency-Constrained Hardware-Aware Quantum Error Correction Co-Design with Adaptive Confidence-Gated Neural Decoding for the Rotated Surface Code [0.0]
  Real-time decoding is a major bottleneck in scaling quantum error correction.<n>We present an adaptive confidence-gated decoding framework that treats decoding as a two-stage inference problem.<n>We benchmark the framework on rotated surface codes with $d in 3,5,7,9,11$ under circuit-level depolarising noise.
  arXiv  Detail & Related papers  (2026-07-07T04:18:42Z)
• Few-Shot Cross-Device Transfer for Quantum Noise Modeling on Real Hardware [0.0]
  We explore transfer learning approaches to apply noise models learned on one quantum device to a different device with the help of a small amount of data.<n>The results show quantum noise can be learned and fine-tuned with minimal samples, and provide a plausible approach to cross-device quantum error mitigation.
  arXiv  Detail & Related papers  (2026-04-27T12:23:14Z)
• Trainable Bitwise Soft Quantization for Input Feature Compression [0.7559720049837458]
  We propose a task-specific, trainable feature quantization layer that compresses the input features of a neural network.<n>This can significantly reduce the amount of data that needs to be transferred from the device to a remote server.
  arXiv  Detail & Related papers  (2026-03-05T13:40:55Z)
• Reducing Storage of Pretrained Neural Networks by Rate-Constrained Quantization and Entropy Coding [56.066799081747845]
  The ever-growing size of neural networks poses serious challenges on resource-constrained devices.<n>We propose a novel post-training compression framework that combines rate-aware quantization with entropy coding.<n>Our method allows for very fast decoding and is compatible with arbitrary quantization grids.
  arXiv  Detail & Related papers  (2025-05-24T15:52:49Z)
• Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth [83.15263499262824]
  We prove that gradient descent converges to a solution that completely disregards the sparse structure of the input. We show how to improve upon Gaussian performance for the compression of sparse data by adding a denoising function to a shallow architecture. We validate our findings on image datasets, such as CIFAR-10 and MNIST.
  arXiv  Detail & Related papers  (2024-02-07T16:32:29Z)
• Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection [58.789823426981044]
  We propose a novel auxiliary loss formulation that aims to align the class confidence of bounding boxes with the accurateness of predictions. Our results reveal that our train-time loss surpasses strong calibration baselines in reducing calibration error for both in and out-domain scenarios.
  arXiv  Detail & Related papers  (2023-03-25T08:56:21Z)
• Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance [50.00102219630088]
  Mixed-precision quantization (MPQ) makes it hard to determine the optimal bit-width for each layer. We propose a joint training scheme that can obtain all indicators at once. For example, MPQ search on ResNet18 with our indicators takes only 0.06 seconds.
  arXiv  Detail & Related papers  (2022-03-16T03:23:50Z)
• Learning with Noisy Labels via Sparse Regularization [76.31104997491695]
  Learning with noisy labels is an important task for training accurate deep neural networks. Some commonly-used loss functions, such as Cross Entropy (CE), suffer from severe overfitting to noisy labels. We introduce the sparse regularization strategy to approximate the one-hot constraint.
  arXiv  Detail & Related papers  (2021-07-31T09:40:23Z)
• AQD: Towards Accurate Fully-Quantized Object Detection [94.06347866374927]
  We propose an Accurate Quantized object Detection solution, termed AQD, to get rid of floating-point computation. Our AQD achieves comparable or even better performance compared with the full-precision counterpart under extremely low-bit schemes.
  arXiv  Detail & Related papers  (2020-07-14T09:07:29Z)

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.