Photonic Quantum-Enhanced Knowledge Distillation

• URL: http://arxiv.org/abs/2603.14898v1
• Date: Mon, 16 Mar 2026 06:59:59 GMT
• Title: Photonic Quantum-Enhanced Knowledge Distillation
• Abstract summary: Photonic Quantum-Enhanced Knowledge Distillation (PQKD) is a hybrid quantum photonic--classical framework.<n>PQKD constrains and guides a parameter-efficient student network during distillation from a high-capacity teacher.
• Score: 23.478631281591692
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Photonic quantum processors naturally produce intrinsically stochastic measurement outcomes, offering a hardware-native source of structured randomness that can be exploited during machine-learning training. Here we introduce Photonic Quantum-Enhanced Knowledge Distillation (PQKD), a hybrid quantum photonic--classical framework in which a programmable photonic circuit generates a compact conditioning signal that constrains and guides a parameter-efficient student network during distillation from a high-capacity teacher. PQKD replaces fully trainable convolutional kernels with dictionary convolutions: each layer learns only a small set of shared spatial basis filters, while sample-dependent channel-mixing weights are derived from shot-limited photonic features and mapped through a fixed linear transform. Training alternates between standard gradient-based optimisation of the student and sampling-robust, gradient-free updates of photonic parameters, avoiding differentiation through photonic hardware. Across MNIST, Fashion-MNIST and CIFAR-10, PQKD traces a controllable compression--accuracy frontier, remaining close to teacher performance on simpler benchmarks under aggressive convolutional compression. Performance degrades predictably with finite sampling, consistent with shot-noise scaling, and exponential moving-average feature smoothing suppresses high-frequency shot-noise fluctuations, extending the practical operating regime at moderate shot budgets.

Related papers

• ScalePredictor: Instance-aware Scale Learning for Accurate Quantization of Vision Transformers [60.09590321091875]
  Post-Training Quantization (PTQ) offers an attractive solution by compressing models using a small calibration set with minimal training overhead.<n>Most existing PTQ works adopt a static quantization paradigm that is uniformly applied to all instances.<n>We propose ScalePredictor, a dynamic quantization framework for accurate and efficient quantization scale learning of ViTs.
  arXiv  Detail & Related papers  (2026-06-20T08:33:55Z)
• Trainable Photonic Measurement for Physics-Informed PDE Learning [8.640731976305544]
  Photonic quantum machine learning offers a route to trainable physical representations built from phase, interference and measurement.<n> Physics-informed neural fields provide a natural setting, because differential equations require trial spaces that preserve phase, frequency and derivative structure.<n>Here we introduce a photonic quantum neural field in which coordinates become trainable optical phases, are mixed by multi-photon Fock-space interference and are decoded from photon-number measurements.
  arXiv  Detail & Related papers  (2026-06-17T05:53:08Z)
• Benchmarking Quantum Extreme Learning based on Gaussian Boson Sampling [0.5161531917413708]
  Reservoir models offer a hardware-efficient learning paradigm for noisy intermediate-scale quantum devices.<n>We propose a quantum extreme learning machine that achieves high classification accuracy while reducing optical resource requirements.
  arXiv  Detail & Related papers  (2026-06-13T10:00:10Z)
• Characterization of errors in photon-heralded quantum operations between non-interacting quantum emitters [0.0]
  We develop an analytic perturbative framework that enables the analysis of small Markovian errors in quantum operations.<n>We benchmark the resulting perturbative predictions on a repeat-until-success CZ gate against numerical simulations.<n>We apply the same framework to analyze coherent phase-shifter miscalibrations as a representative example of optical-manipulation errors.
  arXiv  Detail & Related papers  (2026-06-03T00:39:00Z)
• Medical Imaging Classification with Cold-Atom Reservoir Computing using Auto-Encoders and Surrogate-Driven Training [1.5865523067585527]
  We introduce a hybrid quantum-classical pipeline, based on neutral-atom reservoir computing, for medical image classification.<n>This pipeline learns compact and discriminative representations of image data that are also well-suited for quantum reservoir computing.
  arXiv  Detail & Related papers  (2026-05-07T11:26:09Z)
• 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)
• Continuous-variable photonic quantum extreme learning machines for fast collider-data selection [0.0]
  We study continuous-variable photonic quantum extreme learning machines as fast, low-overhead front-ends for collider data processing.<n>Data is encoded in photonic modes through quadrature displacements and propagated through a fixed-time Gaussian quantum substrate.<n>Only a linear classifier is trained, using a single linear solve, so retraining is fast and the optical path and detector response set the analytical and inference latency.
  arXiv  Detail & Related papers  (2025-10-15T18:21:32Z)
• Wafer-Scale Squeezed-Light Chips [12.435824870106941]
  We report wafer-scale fabrication of two-mode squeezed-vacuum states on a fully complementary metal-oxide-semiconductor (CMOS)-compatible silicon nitride (Si$_3$N$_4$) PIC platform.<n>Across a 4-inch wafer, 8 dies yield 2.9-3.1 dB directly measured quadrature squeezing with $ 0.2$ dB variation, demonstrating excellent uniformity.
  arXiv  Detail & Related papers  (2025-09-12T17:51:51Z)
• A purely Quantum Generative Modeling through Unitary Scrambling and Collapse [6.647966634235082]
  Quantum Scrambling and Collapse Generative Model (QGen) is a purely quantum paradigm that eliminates classical dependencies.<n>We introduce a measurement-based training principle that decomposes learning into tractable subproblems, mitigating barren plateaus.<n> Empirically, QGen outperforms classical and hybrid baselines under matched parameter budget, while maintaining robustness under finite-shot sampling.
  arXiv  Detail & Related papers  (2025-06-12T11:00:21Z)
• Distributed Quantum Neural Networks on Distributed Photonic Quantum Computing [3.299179876684316]
  Photonic quantum neural networks (QNNs) with $M(M+1)/2$ trainable parameters produce high-dimensional probability distributions.<n>Photonic QT achieves an accuracy of $95.50% pm 0.84%$ using 3,292 parameters.<n>Photonic QT outperforms classical compression techniques by 6--12% absolute accuracy.
  arXiv  Detail & Related papers  (2025-05-13T11:58:45Z)
• CALLIC: Content Adaptive Learning for Lossless Image Compression [64.47244912937204]
  CALLIC sets a new state-of-the-art (SOTA) for learned lossless image compression.<n>We propose a content-aware autoregressive self-attention mechanism by leveraging convolutional gating operations.<n>During encoding, we decompose pre-trained layers, including depth-wise convolutions, using low-rank matrices and then adapt the incremental weights on testing image by Rate-guided Progressive Fine-Tuning (RPFT)<n>RPFT fine-tunes with gradually increasing patches that are sorted in descending order by estimated entropy, optimizing learning process and reducing adaptation time.
  arXiv  Detail & Related papers  (2024-12-23T10:41:18Z)
• PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution [95.98801201266099]
  Diffusion-based image super-resolution (SR) models have shown superior performance at the cost of multiple denoising steps.<n>We propose a novel post-training quantization approach with adaptive scale in one-step diffusion (OSD) image SR, PassionSR.<n>Our PassionSR achieves significant advantages over recent leading low-bit quantization methods for image SR.
  arXiv  Detail & Related papers  (2024-11-26T04:49:42Z)
• Experimental quantum natural gradient optimization in photonics [11.72584828456107]
  Variational quantum algorithms (VQAs) promise practical quantum applications in the Noisy Intermediate-Scale Quantum era. The quantum natural gradient (QNG) can achieve faster convergence and avoid local minima more easily. We utilize a fully programmable photonic chip to experimentally estimate the QNG in photonics for the first time.
  arXiv  Detail & Related papers  (2023-10-11T10:41:51Z)
• Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image Recognition [124.80263629921498]
  We propose Pixel Distillation that extends knowledge distillation into the input level while simultaneously breaking architecture constraints. Such a scheme can achieve flexible cost control for deployment, as it allows the system to adjust both network architecture and image quality according to the overall requirement of resources.
  arXiv  Detail & Related papers  (2021-12-17T14:31:40Z)
• Topologically Protecting Squeezed Light on a Photonic Chip [58.71663911863411]
  Integrated photonics offers an elegant way to increase the nonlinearity by confining light strictly inside the waveguide. We experimentally demonstrate the topologically protected nonlinear process of spontaneous four-wave mixing enabling the generation of squeezed light on a silica chip.
  arXiv  Detail & Related papers  (2021-06-14T13:39:46Z)

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.