[2602.02281] A Physical Theory of Backpropagation: Exact Gradients from the Least-Action Principle

Skip to main content

arXiv is now an independent nonprofit!<br>Learn more<br>&times;

Search arXiv

Press Enter to search &middot; Advanced search

-->

Computer Science > Machine Learning

arXiv:2602.02281 (cs)

[Submitted on 2 Feb 2026 (v1), last revised 11 May 2026 (this version, v2)]

Title:A Physical Theory of Backpropagation: Exact Gradients from the Least-Action Principle

Authors:Antonino Emanuele Scurria<br>View a PDF of the paper titled A Physical Theory of Backpropagation: Exact Gradients from the Least-Action Principle, by Antonino Emanuele Scurria

View PDF<br>HTML (experimental)

Abstract:Backpropagation is typically presented as a symbolic procedure: a backward pass topologically distinct from inference, with non-local error signals and synchronous global clocking, features with no clear analog in physical reality. Existing physics-inspired alternatives recover gradients only approximately, in vanishing-perturbation limits, or under weight-symmetry constraints incompatible with feedforward architectures. In this paper, we address this gap by deriving exact backpropagation from Hamilton's least-action principle. By recasting the forward dynamics in continuous time and adapting a Lagrangian formalism for non-conservative systems to the resulting flow, we unify inference and gradient computation within a single variational framework on a doubled phase space, whose two conjugate fields jointly encode activations and sensitivities. A single global Lagrangian governs the dynamics: the task loss enters as a symmetry-breaking perturbation of the forward manifold, and credit assignment emerges as the tension that develops between the conjugate states. Inference and gradient computation thus unfold simultaneously through local interactions, requiring no separate backward circuit. Ultimately, standard backpropagation is recovered exactly as the discrete-time projection of this continuous flow. This perspective unifies the formalism of physics with backpropagation, opening a principled pathway for applying tools from classical mechanics - symplectic geometry, Noether's theorem, path-integral methods - to the analysis of learning dynamics. As a downstream consequence, it also points toward analog and neuromorphic substrates in which learning is embodied in the hardware itself.

Comments:<br>22 pages

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE); Classical Physics (physics.class-ph); Computational Physics (physics.comp-ph)

Cite as:<br>arXiv:2602.02281 [cs.LG]

(or<br>arXiv:2602.02281v2 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2602.02281

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Antonino Emanuele Scurria [view email]<br>[v1]<br>Mon, 2 Feb 2026 16:21:05 UTC (315 KB)

[v2]<br>Mon, 11 May 2026 09:10:38 UTC (308 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled A Physical Theory of Backpropagation: Exact Gradients from the Least-Action Principle, by Antonino Emanuele Scurria<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.LG

next >

new<br>recent<br>| 2026-02

Change to browse by:

cs<br>cs.AI<br>cs.NE<br>physics<br>physics.class-ph<br>physics.comp-ph

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender<br>(What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence,...