Parity Supervision as a Driver of Generalization in Quantum Generative Modeling

• URL: http://arxiv.org/abs/2605.10258v1
• Date: Mon, 11 May 2026 09:24:12 GMT
• Title: Parity Supervision as a Driver of Generalization in Quantum Generative Modeling
• Abstract summary: Generalizing from finite samples to unseen valid states is central to discrete generative modeling.<n>We compare an IQP circuit Born machine trained by parity supervision with the same circuit trained by coordinate-wise mean-squared-error (MSE)<n>Parity supervision improves exact forward Kullback-Leibler (KL) fit and unseen high-value-state recovery over IQP-MSE, while the maximum-entropy control does not reproduce the full effect.
• Score: 3.2007395340330898
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generalizing from finite samples to unseen valid states is central to discrete generative modeling. In a controlled, exactly enumerable setting, we test whether parity losses, commonly used for tractable Instantaneous Quantum Polynomial-time (IQP) training, also provide an inductive bias for generalization. We compare an IQP circuit Born machine trained by parity supervision with the same circuit trained by coordinate-wise mean-squared-error (MSE), and with a classical maximum-entropy control given the same parity moments. Parity supervision improves exact forward Kullback-Leibler (KL) fit and unseen high-value-state recovery over IQP-MSE, while the maximum-entropy control does not reproduce the full effect. A parameter-free spectral reconstruction shows that parity moments already transfer evidence from observed samples to structurally compatible unseen states, which the IQP circuit further refines. This identifies parity supervision not only as a tractable training signal, but also as a generalization mechanism for IQP Born machines when the distribution to be learned, the parity objective, and the circuit architecture are structurally aligned.

Related papers

• Characterizing Large Scale Quantum Systems with Error Per Circuit Layer [0.23398054718043335]
  We introduce Error Per Circuit Layer (EPCL), an overlap-based circuit-level benchmark that estimates an effective layer polarization.<n>We derive the expected overlap decay under an ensemble-averaged depolarizing model and identify the assumptions under which the fitted decay parameter represents an effective layer polarization.<n>Experiments on IBM quantum hardware demonstrate clear EPCL decay in 8- and 16-qubit implementations.
  arXiv  Detail & Related papers  (2026-09-03T17:28:40Z)
• An Agentic Formalization for Certified Quantum Neural Network Design [12.920508545174712]
  We formalize major components of quantum neural network (QNN) theory in a connected lean 4 development.<n>On the expressivity side, we prove exact if-and-only-if characterizations of single-qubit QNNs.<n>On the trainability side, we derive the direct-sum loss-variance law through a de-circular-ized second-moment interface.
  arXiv  Detail & Related papers  (2026-07-14T17:23:31Z)
• Robust Pretty Good Measurement via Hybrid Classical-Quantum Pseudoinverse Approximation and Circuit-Level Realization [0.46976113832881716]
  We introduce a numerically robust PGM formulation based on the Moore-Penrose pseudoinverse.<n>We develop a hybrid classical-quantum framework that combines pseudoinverse-based spectral preprocessing with quantum circuit realizations.
  arXiv  Detail & Related papers  (2026-06-11T10:26:28Z)
• LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs [52.1276403258812]
  We introduce Logit-aware Final-block Quantization (LFQ), a simple yet effective enhancement to block-wise PTQ.<n>LFQ consistently improves the accuracy of complex generation tasks over state-of-the-art block-wise PTQ.
  arXiv  Detail & Related papers  (2026-05-28T11:02:23Z)
• Toward Generative Quantum Utility via Correlation-Complexity Map [10.037801594045519]
  Correlation-Complexity Map for determining when real-world data distributions are structurally aligned with IQP-type quantum generative models.<n>Characterized by two complementary indicators: (i) a Quantum Correlation-Likeness Indicator (QCLI), computed from the dataset's correlation-order (Walsh-Hadamard/Fourier) power spectrum aggregated by interaction order and quantified via Jensen-Shannon divergence from an i.i.d. binomial reference; and (ii) a Classical Correlation-Complexity Indicator (CCI), defined as the fraction of total correlation not captured by the optimal Chow-Liu tree
  arXiv  Detail & Related papers  (2026-03-06T16:25:17Z)
• 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)
• Hybrid Quantum-Classical Recurrent Neural Networks [0.10152838128195468]
  We present a hybrid quantum-classical recurrent neural network architecture.<n>The hidden state is the quantum state of an $n$-qubit quantum circuit (PQC) controlled by a classical feedforward network.<n>We evaluate the model in simulation with up to 14 qubits on sentiment analysis, MNIST, permuted MNIST, copying memory, and language modeling.
  arXiv  Detail & Related papers  (2025-10-29T14:21:49Z)
• Uniformity Bias in Ground-State Sampling Induced by Replica Alignment in Quantum Monte Carlo for Quantum Annealing [0.688204255655161]
  Quantum Monte Carlo (QMC) is widely used to simulate quantum systems.<n>We show that QMC produces uniform ground-state probabilities, unlike QA's biased distribution.<n>This bias originates from replica alignment, caused by the energetic suppression and entropic reduction of kink configurations.
  arXiv  Detail & Related papers  (2025-10-12T12:23:12Z)
• Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty [49.19257648205146]
  We propose an unsupervised conformal inference framework for generation.<n>Our gates achieve close-to-nominal coverage and provide tighter, more stable thresholds than split UCP.<n>The result is a label-free, API-compatible gate for test-time filtering.
  arXiv  Detail & Related papers  (2025-09-26T23:40:47Z)
• ConQuER: Modular Architectures for Control and Bias Mitigation in IQP Quantum Generative Models [40.972673943861075]
  Quantum generative models based on instantaneous quantum (IQP) circuits show great promise in learning complex distributions.<n>Current implementations suffer from lack of controllability over generated outputs and severe generation bias towards certain expected patterns.<n>We present a Controllable Quantum Generative Framework, ConQuER, which addresses both challenges through a modular circuit architecture.
  arXiv  Detail & Related papers  (2025-09-26T16:32:41Z)
• Control landscapes for high-fidelity generation of C-NOT and C-PHASE gates with coherent and environmental driving [41.94295877935867]
  We consider the problem of high fidelity generation of two-qubit C-NOT and C-PHASE (with a detailed study of C-Z) gates in presence of the environment. We study quantum control landscapes which describe the behaviour of the fidelity as a function of the controls.
  arXiv  Detail & Related papers  (2024-05-23T00:04:19Z)
• Direct pulse-level compilation of arbitrary quantum logic gates on superconducting qutrits [36.30869856057226]
  We demonstrate any arbitrary qubit and qutrit gate can be realized with high-fidelity, which can significantly reduce the length of a gate sequence. We show that optimal control gates are robust to drift for at least three hours and that the same calibration parameters can be used for all implemented gates.
  arXiv  Detail & Related papers  (2023-03-07T22:15:43Z)
• Quantum Federated Learning with Entanglement Controlled Circuits and Superposition Coding [44.89303833148191]
  We develop a depth-controllable architecture of entangled slimmable quantum neural networks (eSQNNs) We propose an entangled slimmable QFL (eSQFL) that communicates the superposition-coded parameters of eS-QNNs. In an image classification task, extensive simulations corroborate the effectiveness of eSQFL.
  arXiv  Detail & Related papers  (2022-12-04T03:18:03Z)
• Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers [42.93754828584075]
  We present a new Transformer architecture, Performer, based on Fast Attention Via Orthogonal Random features (FAVOR) Our mechanism scales linearly rather than quadratically in the number of tokens in the sequence, is characterized by sub-quadratic space complexity and does not incorporate any sparsity pattern priors. It provides strong theoretical guarantees: unbiased estimation of the attention matrix and uniform convergence.
  arXiv  Detail & Related papers  (2020-06-05T17:09:16Z)

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.