Programmable k-local Ising Machines and all-optical Kolmogorov-Arnold Networks on Photonic Platforms

• URL: http://arxiv.org/abs/2508.17440v2
• Date: Tue, 02 Sep 2025 10:53:28 GMT
• Title: Programmable k-local Ising Machines and all-optical Kolmogorov-Arnold Networks on Photonic Platforms
• Abstract summary: Photonic computing promises energy-efficient acceleration for optimization and learning.<n>Here we unify k-local Ising optimization and optical Kolmogorov-Arnold network (KAN) learning on a single photonic platform.<n>Key idea is to convert the structural nonlinearity of a nominally linear scatterer into a per-window computational resource.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Photonic computing promises energy-efficient acceleration for optimization and learning, yet discrete combinatorial search and continuous function approximation have largely required distinct devices and control stacks. Here we unify k-local Ising optimization and optical Kolmogorov-Arnold network (KAN) learning on a single photonic platform, establishing a critical convergence point in optical computing. We introduce an SLM-centric primitive that realizes, in one stroke, all-optical k-local Ising interactions and fully optical KAN layers. The key idea is to convert the structural nonlinearity of a nominally linear scatterer into a per-window computational resource by adding a single relay pass through the same spatial light modulator: a folded 4f relay re-images the first Fourier plane onto the SLM so that each selected clique or channel occupies a disjoint window with its own second pass phase patch. Propagation remains linear in the optical field, yet the measured intensity in each window becomes a freely programmable polynomial of the clique sum or projection amplitude. This yields native, per clique k-local couplings without nonlinear media and, in parallel, the many independent univariate nonlinearities required by KAN layers, all trainable with in-situ physical gradients using two frames (forward and adjoint). We outline implementations on spatial photonic Ising machines, injection-locked vertical cavity surface emitting laser (VCSEL) arrays, and Microsoft analog optical computers; in all cases the hardware change is one extra lens and a fold (or an on-chip 4f loop), enabling a minimal overhead, massively parallel route to high-order Ising optimization and trainable, all-optical KAN processing on one platform.

Related papers

• Breaking the Cascade: Compact Nonlinear Optical Computing with Single-Layer Encoder-Decoder Co-Localization [40.4197846036432]
  nonlinear computing can be achieved with a single linear diffractive surface under coherent illumination.<n>We introduce a compact encoder-decoder co-localization architecture in which an input-dependent dynamic encoder and a static optimized decoder are integrated.<n>We experimentally validate the proposed approach using a visible-light optical set-up trained through in situ learning.
  arXiv  Detail & Related papers  (2026-05-31T05:46:10Z)
• Small-scale photonic Kolmogorov-Arnold networks using standard telecom nonlinear modules [0.6219327347402195]
  Photonic neural networks promise ultrafast inference, yet most architectures rely on linear optical meshes with electronic nonlinearities.<n>Here we introduce small-scale photonic Kolmogorov-Arnold networks (SSP-KANs) implemented entirely with standard telecommunications components.<n>SSP-KANs comprising only a few optical modules achieve strong nonlinear inference performance across classification, regression, and image recognition tasks.
  arXiv  Detail & Related papers  (2026-04-09T16:34:58Z)
• Large-scale nonlinear optical computing with incoherent light via linear diffractive systems [46.80331539631633]
  We show that optimized diffractive processors can perform large-scale nonlinear function approximation under spatially incoherent or partially coherent illumination.<n> Numerical results demonstrate snapshot of up to one million distinct nonlinear functions in a single forward pass through a diffractive processor.<n>Our findings establish diffractive processors as a massively parallel universal function approximator for both spatially incoherent and partially coherent illumination.
  arXiv  Detail & Related papers  (2026-03-31T01:27:57Z)
• Separating partially coherent light [0.8932034331007609]
  We demonstrate the automatic separation of spatially partially coherent light into "coherence modes"<n>We use variational processing in layered self-configuring interferometer architectures in a silicon photonic circuit.<n>These results establish a scalable framework for programmable coherence analysis and control in imaging, communication, and photonic information processing.
  arXiv  Detail & Related papers  (2026-03-16T16:43:22Z)
• AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization [84.25316984309725]
  Integration of dynamic, sparse structures with parameter-efficient adapters (e.g., LoRA) is a powerful technique for enhancing Large Language Models (LLMs)<n>Despite minimal increases in computational load, the computation latency often skyrockets, leading to decoding speeds slowing by over 2.5 times.<n>AdaFuse is a framework built on a tight co-design between the algorithm and the underlying hardware system to enable efficient dynamic adapter execution.
  arXiv  Detail & Related papers  (2026-03-12T12:46:42Z)
• GSPN-2: Efficient Parallel Sequence Modeling [101.33780567131716]
  Generalized Spatial Propagation Network (GSPN) addresses this by replacing quadratic self-attention with a line-scan propagation scheme.<n>GSPN-2 establishes a new efficiency frontier for modeling global spatial context in vision applications.
  arXiv  Detail & Related papers  (2025-11-28T07:26:45Z)
• Metasurface-Based Dual-Basis Polarization Beam Splitter for efficient entanglement witnessing [0.0]
  Entanglement witnessing is essential for quantum technologies such as computing, key distribution, and networking.<n>We propose a metasurface-based analyzer that performs dual-basis projections simultaneously by mapping them to spatial modes.<n>The proposed scheme provides a path toward efficient entanglement verification with applications in quantum key distribution, quantum repeaters, and scalable quantum networks.
  arXiv  Detail & Related papers  (2025-10-04T20:23:25Z)
• Spatially Parallel All-optical Neural Networks [14.284567977850912]
  All-optical neural networks (AONNs) have emerged as a promising paradigm for ultrafast and energy-efficient computation.<n>Here we propose a spatially parallel architecture for all-optical neural networks (SP-AONNs)<n>Our findings highlight spatial parallelism as a practical and scalable strategy for advancing the capabilities of optical neural computing.
  arXiv  Detail & Related papers  (2025-09-28T03:25:40Z)
• Massively parallel and universal approximation of nonlinear functions using diffractive processors [17.16859564691328]
  Large-scale nonlinear computation can be performed using linear optics through optimized diffractive processors composed of passive phase-only surfaces.<n>We numerically demonstrate the parallel computation of one million distinct nonlinear functions, accurately executed at wavelength-scale spatial density.<n>These results establish diffractive optical processors as a scalable platform for massively parallel universal nonlinear function approximation.
  arXiv  Detail & Related papers  (2025-07-11T01:54:10Z)
• Joint Transmit and Pinching Beamforming for Pinching Antenna Systems (PASS): Optimization-Based or Learning-Based? [89.05848771674773]
  A novel antenna system ()-enabled downlink multi-user multiple-input single-output (MISO) framework is proposed.<n>It consists of multiple waveguides, which equip numerous low-cost antennas, named (PAs)<n>The positions of PAs can be reconfigured to both spanning large-scale path and space.
  arXiv  Detail & Related papers  (2025-02-12T18:54:10Z)
• Successive optimization of optics and post-processing with differentiable coherent PSF operator and field information [9.527960631238173]
  We introduce a precise optical simulation model, and every operation in pipeline is differentiable.<n>To efficiently address various degradation, we design a joint optimization procedure that leverages field information.
  arXiv  Detail & Related papers  (2024-12-19T07:49:40Z)
• GP-FL: Model-Based Hessian Estimation for Second-Order Over-the-Air Federated Learning [52.295563400314094]
  Second-order methods are widely adopted to improve the convergence rate of learning algorithms.<n>This paper introduces a novel second-order FL framework tailored for wireless channels.
  arXiv  Detail & Related papers  (2024-12-05T04:27:41Z)
• Generalizable Non-Line-of-Sight Imaging with Learnable Physical Priors [52.195637608631955]
  Non-line-of-sight (NLOS) imaging has attracted increasing attention due to its potential applications. Existing NLOS reconstruction approaches are constrained by the reliance on empirical physical priors. We introduce a novel learning-based solution, comprising two key designs: Learnable Path Compensation (LPC) and Adaptive Phasor Field (APF)
  arXiv  Detail & Related papers  (2024-09-21T04:39:45Z)
• Measuring, processing, and generating partially coherent light with self-configuring optics [4.574373524692042]
  We present a universal method to analyze, process, and generate spatially partially coherent light in multimode systems. Our method relies on cascaded self-configuring layers whose average power outputs are sequentially optimized. We show how this method can be used to perform partially coherent environmental light sensing, generation of multimode partially coherent light with arbitrary coherency matrices, and unscrambling of quantum optical mixtures.
  arXiv  Detail & Related papers  (2024-02-01T15:59:49Z)
• All-optical modulation with single-photons using electron avalanche [66.27103948750306]
  We demonstrate all-optical modulation enabled by electron avalanche process in silicon.<n>Our approach opens the possibility of gigahertz-speed, and potentially even faster, optical switching at the single-photon level.
  arXiv  Detail & Related papers  (2023-12-18T20:14:15Z)
• Complex-valued universal linear transformations and image encryption using spatially incoherent diffractive networks [0.0]
  As an optical processor, a Diffractive Deep Neural Network (D2NN) utilizes engineered diffractive surfaces designed through machine learning to perform all-optical information processing. We show that a spatially incoherent diffractive visual processor can approximate any complex-valued linear transformation and be used for all-optical image encryption using incoherent illumination.
  arXiv  Detail & Related papers  (2023-10-05T08:43:59Z)
• Dynamic Frame Interpolation in Wavelet Domain [57.25341639095404]
  Video frame is an important low-level computation vision task, which can increase frame rate for more fluent visual experience. Existing methods have achieved great success by employing advanced motion models and synthesis networks. WaveletVFI can reduce computation up to 40% while maintaining similar accuracy, making it perform more efficiently against other state-of-the-arts.
  arXiv  Detail & Related papers  (2023-09-07T06:41:15Z)
• Shaping Single Photons through Multimode Optical Fibers using Mechanical Perturbations [55.41644538483948]
  We show an all-fiber approach for controlling the shape of single photons and the spatial correlations between entangled photon pairs. We optimize these perturbations to localize the spatial distribution of a single photon or the spatial correlations of photon pairs in a single spot.
  arXiv  Detail & Related papers  (2023-06-04T07:33:39Z)
• Universal Linear Intensity Transformations Using Spatially-Incoherent Diffractive Processors [0.0]
  Under spatially-incoherent light, a diffractive optical network can be designed to perform arbitrary complex-valued linear transformations. We numerically demonstrate that a spatially-incoherent diffractive network can be trained to all-optically perform any arbitrary linear intensity transformation.
  arXiv  Detail & Related papers  (2023-03-23T04:51:01Z)
• Optical Spin Initialisation and Readout with a Cavity-Coupled Quantum Dot in an In-Plane Magnetic Field [0.0]
  We show that a cavity with a single, linearly-polarised mode can simultaneously support both high-fidelity optical spin initialisation and readout in a single, in-plane (Voigt geometry) magnetic field. Our analysis provides optimal parameter regimes for high-fidelity initialisation and readout, and coherent control in both cavity configurations.
  arXiv  Detail & Related papers  (2022-06-22T12:14:24Z)
• All-optical graph representation learning using integrated diffractive photonic computing units [51.15389025760809]
  Photonic neural networks perform brain-inspired computations using photons instead of electrons. We propose an all-optical graph representation learning architecture, termed diffractive graph neural network (DGNN) We demonstrate the use of DGNN extracted features for node and graph-level classification tasks with benchmark databases and achieve superior performance.
  arXiv  Detail & Related papers  (2022-04-23T02:29:48Z)
• Rapid characterisation of linear-optical networks via PhaseLift [51.03305009278831]
  Integrated photonics offers great phase-stability and can rely on the large scale manufacturability provided by the semiconductor industry. New devices, based on such optical circuits, hold the promise of faster and energy-efficient computations in machine learning applications. We present a novel technique to reconstruct the transfer matrix of linear optical networks.
  arXiv  Detail & Related papers  (2020-10-01T16:04:22Z)

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.