A Conservation Law for Equilibrium Propagation and Coupled Learning

Joshua A. McGinnis; Adam G. Kline; Yoichiro Mori

math.OCJun 13, 2026

A Conservation Law for Equilibrium Propagation and Coupled Learning

Authors: Joshua A. McGinnis, Adam G. Kline, Yoichiro Mori

Organizations: Department of Mathematics, University of Pennsylvania, Philadelphia, PA, USA · Department of Physics & Astronomy, University of Pennsylvania, Philadelphia, PA, USA · Department of Biology, University of Pennsylvania, Philadelphia, PA, USA

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. We prove that this conservation holds in a broad range of physically relevant settings. We then show that the conservation law constrains the training dynamics in a way that makes convergence reliable in important settings for linear circuits. We conclude by discussing some practical implications of this conservation law.

Explore similar work

Conservation laws determine what physical learning remembers
Jul 30, 2026Bijaya DangolInductive Bias Environment
Coercivity and Local Convergence of Physical Learning in Linear Circuits
Jun 13, 2026Joshua A. McGinnis, Xinbo Li, Yoichiro MoriCircuits Networked Systems
Reciprocity Separates Gradient Flow from Rotation in Conservative Physical Learning
Aug 31, 2026Ruiwu Niu, Xiaowen Bi, Michaël Antonie van WykGradient Flow Wasserstein Gradient Flows

Jul 30, 2026 · cond-mat.softJ/K move · Enter open · S save

Conservation laws determine what physical learning remembers

Bijaya Dangol

1Independent researcher

Physical learning rules such as equilibrium propagation (EP), coupled learning (CL), and adjoint coupled learning (AL) train resistive networks through local measurements. In the small-nudge limit EP and CL exactly conserve the conductance mass K = (1/2) sum_e kappa_e^2, a property that stabilizes training. We show that conservation also governs the inductive bias of these rules. For a single output we prove that EP and CL are trajectory equivalent, so single-output experiments cannot distinguish what the two rules learn. We prove that AL does not conserve the mass but dissipates it at exactly twice its own loss. In linear circuits we prove that the conserved mass has no functional consequence: all three vector fields are homogeneous in the conductances, so the selected solution is independent of the initialization scale. Fixed nonlinear elements break this protection. In diode circuits the learned input-output function depends on the initialization scale by up to about forty percent, an effect absent in linear controls, and the conservative rules retain this memory permanently while the dissipative rule partially erases it. At matched training loss the dissipative rule typically generalizes worse than the conservative rules, although it reaches low training loss faster; the penalty correlates with the mass dissipated en route and fades in larger circuits, where little mass is lost. The conservation structure of a local learning rule thus sets its initialization memory, its training speed, and, where dissipation is appreciable, its generalization; it should be treated as a design parameter of physical learning machines.

Inductive Bias Environment

Open paper Ask about it PDF

Abstract

Explore similar work

Conservation laws determine what physical learning remembers

Coercivity and Local Convergence of Physical Learning in Linear Circuits

Reciprocity Separates Gradient Flow from Rotation in Conservative Physical Learning