Perturbative Contrastive Physical Learning

• URL: http://arxiv.org/abs/2606.09756v1
• Date: Mon, 08 Jun 2026 17:14:07 GMT
• Title: Perturbative Contrastive Physical Learning
• Abstract summary: Perturbative Contrastive Physical Learning (PCPL) is a general framework in which learning emerges from measurable contrasts between physical states.<n>We show that PCPL can reflect either local sensitivities or global inverse-problem structure, yet do not require centralized gradient computation.<n>We demonstrate PCPL in two platforms: (i) spring networks that update bond stiffness using measured displacements and forces, and (ii) continuous-variable photonic circuits trained via quad xrature measurements and finite-difference estimates of the Jacobian.
• Score: 1.3831855739681835
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Responses to perturbations are key to understanding physical systems. The ability to contrast such responses by comparing how a system reacts under slightly different conditions provides a mechanism for learning. Here, we introduce Perturbative Contrastive Physical Learning (PCPL), a general framework in which learning emerges from measurable contrasts between physical states produced by controlled changes to inputs, boundary conditions, parameters, or interpreter functions. PCPL unifies and extends prior approaches: Equilibrium Propagation is rooted in contrasts between free and nudged equilibria in energy-based systems, while Frequency Propagation corresponds to contrasts extracted from sinusoidally driven, frequency-demodulated responses. We show that contrast-driven updates can reflect either local sensitivities or global inverse-problem structure, yet do not require centralized gradient computation. Instead, effective learning geometry emerges implicitly from the system's own physical response, allowing learning behavior to arise without an external processor or explicit backpropagation. We demonstrate PCPL in two platforms: (i) spring networks that update bond stiffness using measured displacements and forces, and (ii) continuous-variable photonic circuits trained via x quadrature measurements and finite-difference estimates of the Jacobian. Both platforms successfully learn classification tasks. We further show that a continuous-variable photonic circuit can be trained to implement analog multiplication, illustrating a step toward more autonomous physical learning systems.

Related papers

• On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking [49.1352577985191]
  We present a comprehensive analysis of how two-layer neural networks learn features to solve the modular addition task.<n>Our work provides a full mechanistic interpretation of the learned model and a theoretical explanation of its training dynamics.
  arXiv  Detail & Related papers  (2026-02-18T20:25:13Z)
• Near-Equilibrium Propagation training in nonlinear wave systems [0.0]
  Backpropagation learning algorithm, the workhorse of modern artificial intelligence, is notoriously difficult to implement in physical neural networks.<n>We extend EP learning to both discrete and continuous complex-valued wave systems.<n> Numerical studies on standard benchmarks, including a simple logical task and handwritten-digit recognition, demonstrate stable convergence.
  arXiv  Detail & Related papers  (2025-10-17T15:03:07Z)
• Information-Theoretic Bounds and Task-Centric Learning Complexity for Real-World Dynamic Nonlinear Systems [0.6875312133832079]
  Dynamic nonlinear systems exhibit distortions arising from coupled static and dynamic effects.<n>This paper presents a theoretical framework grounded in structured decomposition, variance analysis, and task-centric complexity bounds.
  arXiv  Detail & Related papers  (2025-09-08T12:08:02Z)
• Model-free learning of probability flows: Elucidating the nonequilibrium dynamics of flocking [15.238808518078567]
  High dimensionality of the phase space renders traditional computational techniques infeasible for estimating the entropy production rate. We derive a new physical connection between the probability current and two local definitions of the EPR for inertial systems. Our results highlight that entropy is consumed on the spatial interface of a flock as the interplay between alignment and fluctuation dynamically creates and annihilates order.
  arXiv  Detail & Related papers  (2024-11-21T17:08:06Z)
• Learning Controlled Stochastic Differential Equations [61.82896036131116]
  This work proposes a novel method for estimating both drift and diffusion coefficients of continuous, multidimensional, nonlinear controlled differential equations with non-uniform diffusion. We provide strong theoretical guarantees, including finite-sample bounds for (L2), (Linfty), and risk metrics, with learning rates adaptive to coefficients' regularity. Our method is available as an open-source Python library.
  arXiv  Detail & Related papers  (2024-11-04T11:09:58Z)
• A distributional simplicity bias in the learning dynamics of transformers [50.91742043564049]
  We show that transformers, trained on natural language data, also display a simplicity bias.<n>Specifically, they sequentially learn many-body interactions among input tokens, reaching a saturation point in the prediction error for low-degree interactions.<n>This approach opens up the possibilities of studying how interactions of different orders in the data affect learning, in natural language processing and beyond.
  arXiv  Detail & Related papers  (2024-10-25T15:39:34Z)
• Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens [9.590540796223715]
  In this paper, we attempt to explore the in-context learning process in Transformers through a lens of representation learning. The ICL inference process of the attention layer aligns with the training procedure of its dual model, generating token representation predictions. We extend our theoretical conclusions to more complicated scenarios, including one Transformer layer and multiple attention layers.
  arXiv  Detail & Related papers  (2023-10-20T01:55:34Z)
• Emergent learning in physical systems as feedback-based aging in a glassy landscape [0.0]
  We show that the learning dynamics resembles an aging process, where the system relaxes in response to repeated application of the feedback boundary forces. We also observe that the square root of the mean-squared error as a function of epoch takes on a non-exponential form, which is a typical feature of glassy systems.
  arXiv  Detail & Related papers  (2023-09-08T15:24:55Z)
• Machine learning in and out of equilibrium [58.88325379746631]
  Our study uses a Fokker-Planck approach, adapted from statistical physics, to explore these parallels. We focus in particular on the stationary state of the system in the long-time limit, which in conventional SGD is out of equilibrium. We propose a new variation of Langevin dynamics (SGLD) that harnesses without replacement minibatching.
  arXiv  Detail & Related papers  (2023-06-06T09:12:49Z)
• Contrastive-Signal-Dependent Plasticity: Self-Supervised Learning in Spiking Neural Circuits [61.94533459151743]
  This work addresses the challenge of designing neurobiologically-motivated schemes for adjusting the synapses of spiking networks. Our experimental simulations demonstrate a consistent advantage over other biologically-plausible approaches when training recurrent spiking networks.
  arXiv  Detail & Related papers  (2023-03-30T02:40:28Z)
• Composable Learning with Sparse Kernel Representations [110.19179439773578]
  We present a reinforcement learning algorithm for learning sparse non-parametric controllers in a Reproducing Kernel Hilbert Space. We improve the sample complexity of this approach by imposing a structure of the state-action function through a normalized advantage function. We demonstrate the performance of this algorithm on learning obstacle-avoidance policies in multiple simulations of a robot equipped with a laser scanner while navigating in a 2D environment.
  arXiv  Detail & Related papers  (2021-03-26T13:58:23Z)
• Strictly Batch Imitation Learning by Energy-based Distribution Matching [104.33286163090179]
  Consider learning a policy purely on the basis of demonstrated behavior -- that is, with no access to reinforcement signals, no knowledge of transition dynamics, and no further interaction with the environment. One solution is simply to retrofit existing algorithms for apprenticeship learning to work in the offline setting. But such an approach leans heavily on off-policy evaluation or offline model estimation, and can be indirect and inefficient. We argue that a good solution should be able to explicitly parameterize a policy, implicitly learn from rollout dynamics, and operate in an entirely offline fashion.
  arXiv  Detail & Related papers  (2020-06-25T03:27:59Z)
• Watch and learn -- a generalized approach for transferrable learning in deep neural networks via physical principles [0.0]
  We demonstrate an unsupervised learning approach that achieves fully transferrable learning for problems in statistical physics across different physical regimes. By coupling a sequence model based on a recurrent neural network to an extensive deep neural network, we are able to learn the equilibrium probability distributions and inter-particle interaction models of classical statistical mechanical systems.
  arXiv  Detail & Related papers  (2020-03-03T18:37:23Z)

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.