Pith. sign in

REVIEW 3 cited by

Local Learning Rules for Out-of-Equilibrium Physical Generative Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.19136 v4 pith:TDY3SR3O submitted 2025-06-23 cs.LG cond-mat.mes-hallcs.ETcs.NE

classification cs.LGcond-mat.mes-hallcs.ETcs.NE
keywords drivinggenerativelearninglocalmodelsnetworkout-of-equilibriumprotocol
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We show that the out-of-equilibrium driving protocol of score-based generative models (SGMs) can be learned via local learning rules. The gradient with respect to the parameters of the driving protocol is computed directly from force measurements or from observed system dynamics. As a demonstration, we implement an SGM in a network of driven, nonlinear, overdamped oscillators coupled to a thermal bath. We first apply it to the problem of sampling from a mixture of two Gaussians in 2D. Finally, we train an oscillator network on the MNIST dataset to generate images of handwritten digits 0 and 1.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Embodying computation in nonlinear perturbative metamaterials

    cond-mat.mes-hall 2025-09 conditional novelty 7.0 of 10

    A nonlinear coordinate transformation lets designers turn nonlinear tight-binding computing models into physical metamaterial geometries.

  2. A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computing

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Tunable energy landscapes whose thermal averages equal sigmoid, softmax, and matrix-vector products can, in principle, form the basis of a low-energy analog computer, with a superconducting double-well device as a fir...

  3. Solving the compute crisis with physics-based ASICs

    cs.ET 2025-07 unverdicted novelty 4.0 of 10

    A coalition of academic and industry researchers argues that chips exploiting natural physical dynamics, rather than enforcing digital abstractions, could dramatically cut AI computing costs.

Pith tools