Information Processing Capacity of Stationary Physical Systems: Theory, Data-efficient Estimation Methods, and Photonic Demonstration

• URL: http://arxiv.org/abs/2605.19152v2
• Date: Thu, 21 May 2026 13:18:25 GMT
• Title: Information Processing Capacity of Stationary Physical Systems: Theory, Data-efficient Estimation Methods, and Photonic Demonstration
• Abstract summary: We extend the Information Processing Capacity framework to stationary physical computing systems.<n>We validate the framework experimentally using a photonic computing system based on picosecond laser pulses propagating through a nonlinear optical fibre.<n>These results establish IPC as a practical bridge between the dynamics of physical computing systems and their machine-learning performance.
• Score: 0.8602553195689513
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Physical computing systems provide a promising route toward hardware-native machine learning, but their computational capabilities remain difficult to characterize in a principled, task-independent, and data-efficient way. We extend the Information Processing Capacity (IPC) framework to stationary physical computing systems and establish several fundamental results: individual capacities are bounded between zero and one, their sum over a complete basis is bounded by the number of readouts, and noise strictly reduces this bound. We address the finite-sample estimation of IPC and derive the asymptotic form of the systematic positive bias affecting naive estimators. Building on these results, we introduce data-efficient estimation methods based on Richardson extrapolation and Sobol quasi-random sampling. We validate the framework experimentally using a photonic computing system based on picosecond laser pulses propagating through a nonlinear optical fibre. By varying the laser power and fibre length, we observe systematic shifts of the IPC distribution toward higher-order nonlinear capacities induced by the Kerr effect. Finally, we demonstrate that the total IPC strongly correlates with performance on benchmark machine-learning tasks and provides a reliable estimate of the effective dimensionality of the system. These results establish IPC as a practical bridge between the intrinsic dynamics of physical computing systems and their machine-learning performance.

Related papers

• Efficient Machine Unlearning via Influence Approximation [75.31015485113993]
  Influence-based unlearning has emerged as a prominent approach to estimate the impact of individual training samples on model parameters without retraining.<n>This paper establishes a theoretical link between memorizing (incremental learning) and forgetting (unlearning)<n>We introduce the Influence Approximation Unlearning algorithm for efficient machine unlearning from the incremental perspective.
  arXiv  Detail & Related papers  (2025-07-31T05:34:27Z)
• Reservoir Computing with a Single Oscillating Gas Bubble: Emphasizing the Chaotic Regime [0.0]
  We propose and theoretically validate a reservoir computing system based on a single bubble trapped within a bulk of liquid.<n>By applying an external acoustic pressure wave to both encode input information and excite the complex nonlinear dynamics, we showcase the ability of this single-bubble reservoir computing system to forecast complex benchmarking time series.
  arXiv  Detail & Related papers  (2025-03-25T23:32:09Z)
• Blending Optimal Control and Biologically Plausible Learning for Noise-Robust Physical Neural Networks [0.9423257767158634]
  Physical neural networks (PNNs) offer efficient neuromorphic information processing.<n>We propose a training approach for substantially reducing this training cost.<n>In addition to the reduction of training time, this approach achieves robust processing even under measurement errors and noise.
  arXiv  Detail & Related papers  (2025-02-26T11:10:40Z)
• A Comparative Study of Machine Learning Models Predicting Energetics of Interacting Defects [5.574191640970887]
  We present a comparative study of three different methods to predict the free energy change of systems with interacting defects. Our findings indicate that the cluster expansion model can achieve precise energetics predictions even with this limited dataset. This research provide a preliminary evaluation of applying machine learning techniques in imperfect surface systems.
  arXiv  Detail & Related papers  (2024-03-20T02:15:48Z)
• High-performance real-world optical computing trained by in situ gradient-based model-free optimization [2.2407602847819827]
  We propose a gradient-based model-free optimization (G-MFO) method based on a Monte Carlo gradient estimation algorithm. G-MFO treats an optical computing system as a black box and back-propagates the loss directly to the optical computing weights' probability distributions. Our experiments on diffractive optical computing systems show that G-MFO outperforms hybrid training on the MNIST and FMNIST datasets.
  arXiv  Detail & Related papers  (2023-07-22T01:56:58Z)
• Machine learning at the mesoscale: a computation-dissipation bottleneck [77.34726150561087]
  We study a computation-dissipation bottleneck in mesoscopic systems used as input-output devices. Our framework sheds light on a crucial compromise between information compression, input-output computation and dynamic irreversibility induced by non-reciprocal interactions.
  arXiv  Detail & Related papers  (2023-07-05T15:46:07Z)
• Robustness and Generalization Performance of Deep Learning Models on Cyber-Physical Systems: A Comparative Study [71.84852429039881]
  Investigation focuses on the models' ability to handle a range of perturbations, such as sensor faults and noise. We test the generalization and transfer learning capabilities of these models by exposing them to out-of-distribution (OOD) samples.
  arXiv  Detail & Related papers  (2023-06-13T12:43:59Z)
• Pseudo-Spherical Contrastive Divergence [119.28384561517292]
  We propose pseudo-spherical contrastive divergence (PS-CD) to generalize maximum learning likelihood of energy-based models. PS-CD avoids the intractable partition function and provides a generalized family of learning objectives.
  arXiv  Detail & Related papers  (2021-11-01T09:17:15Z)
• An Extensible Benchmark Suite for Learning to Simulate Physical Systems [60.249111272844374]
  We introduce a set of benchmark problems to take a step towards unified benchmarks and evaluation protocols. We propose four representative physical systems, as well as a collection of both widely used classical time-based and representative data-driven methods.
  arXiv  Detail & Related papers  (2021-08-09T17:39:09Z)
• Linear embedding of nonlinear dynamical systems and prospects for efficient quantum algorithms [74.17312533172291]
  We describe a method for mapping any finite nonlinear dynamical system to an infinite linear dynamical system (embedding) We then explore an approach for approximating the resulting infinite linear system with finite linear systems (truncation)
  arXiv  Detail & Related papers  (2020-12-12T00:01:10Z)
• Information Processing Capacity of Spin-Based Quantum Reservoir Computing Systems [0.0]
  Quantum reservoir computing (QRC) with Ising spin networks was introduced as a quantum version of classical reservoir computing. We characterize the performance of the spin-based QRC model with the Information Processing Capacity (IPC) This work establishes a clear picture of the computational capabilities of a quantum network of spins for reservoir computing.
  arXiv  Detail & Related papers  (2020-10-13T13:26:34Z)

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.