physics.app-phNov 12, 2026

Contrastive local learning in large nonlinear analog circuits

Authors: Pragyan Pandey, Peter Wu, Deema Alyahya, Eric Y. Ma

Organizations: Department of Physics, University of California, Berkeley, California 94720, USA · Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, California 94720, USA · Lawrence Berkeley National Laboratory, Berkeley, California 94720, USA

Abstract

Machine learning in physical hardware promises to reduce training cost by colocating computation, memory and adaptation within device physics. Contrastive local learning networks (CLLNs) offer a compelling route: an electrical circuit relaxes to equilibrium in free and weakly clamped states, and each adaptive element updates from local voltage contrasts rather than backpropagated error signals. Yet whether nonlinear transistor implementations can scale beyond proof-of-concept circuits, and what design principles control that scaling, have remained unknown. Here we show that nonlinear analog circuits trained by contrastive local rules can learn larger machine-learning tasks and remain robust under hardware nonidealities. Using device-level circuit simulations, we systematically explore initialization, operating regime, loss-dependent clamping and training parameters, and scale CLLNs beyond ten thousand adaptive edges. The same local rule trains classifiers that reach the accuracy regime of conventional digital methods on Ionosphere and handwritten-digit benchmarks, and a network that autoregressively generates language over a 122-token vocabulary. These results establish the feasibility of local learning in large nonlinear analog circuits.

Figures & tables

Explore similar work

CardsList
  1. Coercivity and Local Convergence of Physical Learning in Linear Circuits

    Jun 13, 2026Joshua A. McGinnis, Xinbo Li, Yoichiro MoriEquilibrium PropagationOptimization Convergence Analysis

  2. Lock-in EP: An In-Situ Training Algorithm for Oscillatory Hardware

    Oct 5, 2026Sowjanya Tammali, Wilkie Olin-AmmentorpAnalog ComputingEquilibrium Propagation

  3. KCLNet: Electrically Equivalence-Oriented Graph Representation Learning for Analog Circuits

    Mar 25, 2026Peng Xu, Yapeng Li, Tinghuan Chen +2Representation LearningGraph Representation Learning