arXiv:2606. 15444v1 Announce Type: cross Abstract: In this paper we show that the physical learning methods known as coupled learning (CL) and equilibrium propagation (EP) conserve a mass-like quantity in the trainable parameters in the continuous-time, small-nudging limit.
arXiv:2606. 15443v1 Announce Type: cross Abstract: Physical learning methods train physical networks to perform computational tasks using only local update rules, exploiting the physics of the system to handle the global transfer of information.
arXiv:2608. 00097v1 Announce Type: cross Abstract: Physical learning rules such as equilibrium propagation (EP), coupled learning (CL), and adjoint coupled learning (AL) train resistive networks through local measurements.
arXiv:2602. 03670v2 Announce Type: replace-cross Abstract: Equilibrium Propagation (EP) is a physics-inspired learning algorithm that uses stationary states of a dynamical system both for inference and learning.
The paper investigates how two independent inductive biases—one from the circuit’s invariance under conductance rescaling and one from the learning rule’s conservation of a mass quantity—affect what a physical learning system remembers. By separating these effects, the authors show that when every element is trainable, the initialization scale has negligible influence on the learned function, whereas a single untrainable element can cause the function to shift significantly with initialization. They further demonstrate that the conservation law does not protect memory but instead influences solution quality, with adjoint coupled learning (AL) generally performing worse than equilibrium propagation (EP) and coupled learning (CL) in small circuits. whyItMatters":"The study clarifies that only the circuit’s structural bias, not the rule’s conservation property, determines memory retention in physical learning systems."
arXiv:2609.05808v1 Announce Type: cross Abstract: In situ adjoint training extracts parameter gradients directly from measurement, but has so far been limited to reciprocal or restricted systems. Her...
arXiv:2608.30778v1 Announce Type: new Abstract: Physical learning lets a trainable material or network use its own physical response to carry error signals, reducing the need for a separately program...
The paper investigates gradient descent dynamics in the Edge of Stability regime, where a large learning rate causes persistent oscillations linked to improved generalization. It introduces a tractable continuous‑time mean–fluctuation model that couples the window‑averaged trajectory with its fluctuation covariance, derives this model rigorously from a sharp‑valley framework, and analyzes its stationary states and linear stability. The authors also extend the model to wide two‑layer networks, deriving a Wasserstein‑2 gradient flow for weights and fluctuations, proving well‑posedness, a mean‑field limit, and conditional convergence results, with numerical experiments illustrating the predictions and finite‑time limitations.
The review explores how control theory, optimal transport, probabilistic inference, non‑equilibrium thermodynamics, and machine learning are interconnected through the optimization of free‑energy‑like functionals under dynamical or statistical constraints. It presents a conceptual thread linking these five fields and illustrates the ideas with applications in reinforcement learning, variational inference, and generative modeling. The article is written for readers without prior familiarity, beginning with physics principles.
arXiv:2401. 04013v2 Announce Type: replace Abstract: Deep learning models, such as wide neural networks, can be conceptualized as nonlinear dynamical physical systems characterized by a multitude of interacting degrees of freedom.
arXiv:2606. 00340v1 Announce Type: new Abstract: We study optimal learning-rate selection in two-layer and three-layer linear neural networks trained to learn linear target functions.
arXiv:2510. 16084v3 Announce Type: replace Abstract: Backpropagation learning algorithm, the workhorse of modern artificial intelligence, is notoriously difficult to implement in physical neural networks.
arXiv:2606. 29519v1 Announce Type: new Abstract: Long-range learning is hard for recurrent networks trained with stochastic gradient descent, because the influence of a past input fades with the lag $\ell$, and if it fades too fast the dependence cannot be learned from finite data.