Thermodynamic Computing

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 11

All topics

Online local learning for generative thermodynamic computing
Sep 14, 2026Huilin Wang, Weibing DengThermodynamic Computing Local Learning
Key Laboratory of Quark and Lepton Physics (MOE) and Institute of Particle Physics, Central China Normal University, Wuhan 430079, China
The thermodynamic freedom of a thermodynamic computer
Aug 28, 2026Stephen WhitelamEfficient Inference Thermodynamic Computing
Molecular Foundry, Lawrence Berkeley National Laboratory, 1 Cyclotron Road, Berkeley, CA 94720, USA
Thermalizing Stochastic Programs
Aug 3, 2026Mirko Amico, Andraž Jelinčič, Colin Oscar Nancarrow +6Thermodynamic Computing Energy-Efficient ML
Extropic Corporation, San Francisco, California 94111, USA · CUNY Graduate Center, New York, NY, USA
CN101 - A Digital Thermodynamic Computer for Generative AI
Aug 1, 2026Lars Holdijk, Denis Melanson, Zier Mensch +14Thermodynamic Computing
Normal Computing Corporation, New York, USA · University of Oxford, Oxford, United Kingdom · University of Amsterdam, Amsterdam, Netherlands +2
A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computing
Jul 17, 2026Owen Lockwood, Jérémy Béjanin, Joost Bus +4Thermodynamic Computing Energy-Efficient ML
Extropic Corporation, San Francisco, California 94111, USA · 2Noumenal Labs Inc, Dallas, Texas 75229, USA · 1Extropic Corporation, San Francisco, California 94111, USA +1
Moment-Resolved Readout and Reservoir Diversity in Nonequilibrium Langevin Computing
Jul 16, 2026JiZheng Duan, MingYang Zhao, YanWei Chen +1Thermodynamic Computing Reservoir Computing
Institute of Modern Physics, Chinese Academy of Sciences
Scaling Up Thermodynamic AI Models
Jun 30, 2026Andrew G. MooreEfficient Neural Network Inference AI Accelerator Inference
Energy-efficient codon optimization on thermodynamic hardware
Jun 15, 2026Andraz Jelincic, Ross C. WalkerThermodynamic Computing Ising Model
1Extropic Corp., Boston, MA
Thermodynamic Networks: Harnessing Non-Equilibrium Steady States for Computation
May 15, 2026Patryk Lipka-Bartosik, Gianmichele Blasi, Javier Lalueza Puértolas +3Thermodynamic Computing
Center for Theoretical Physics, Polish Academy of Sciences, Warsaw, Poland · Instituto de Física Interdisciplinar y Sistemas Complejos IFISC (CSIC-UIB), E-07122 Palma de Mallorca, Spain · Física Teòrica: Informació i Fenòmens Quàntics, Department de Física, Universitat Autònoma de Barcelona, 08193 Bellaterra (Barcelona), Spain +1
Symmetric Equilibrium Propagation for Thermodynamic Diffusion Training
Apr 26, 2026Aditi DeEquilibrium Propagation Thermodynamic Computing
Evolutionary design of thermodynamic logic gates and their heat emission
Feb 13, 2026Stephen WhitelamThermodynamic Computing
Molecular Foundry, Lawrence Berkeley National Laboratory, 1 Cyclotron Road, Berkeley, CA 94720, USA

Sep 14, 2026, physics.data-anJ/K move · Enter open · S save

Online local learning for generative thermodynamic computing

Huilin Wang, Weibing Deng

Key Laboratory of Quark and Lepton Physics (MOE) and Institute of Particle Physics, Central China Normal University, Wuhan 430079, China

Thermodynamic Computing Local Learning Online Learning

Open paper AskPDF arXiv

Generative thermodynamic computers turn thermal noise into structured data through Langevin dynamics. We train these systems with a local update at each integration step. The reverse-path Onsager-Machlup objective yields a coupling gradient that is a symmetric sum of local residual-state correlations. We apply this gradient immediately rather than accumulating it over a full trajectory. In digital simulations using MNIST prototypes, online and trajectory-batch training reach similar validation losses on fixed noising paths. Models trained online release less heat on average in all five independently seeded pairs, with both models' parameters held fixed during sampling. Auxiliary classifier and nearest-prototype measures change modestly, while pairwise diversity decreases. The response to noise depends strongly on where the errors enter: independent zero-mean errors in the formed updates produce little heat change over a finite range of noise amplitudes, whereas residual offset and temporal correlation have much larger effects. Storing trained couplings requires substantially less precision than resolving deterministic updates during training. Together, these results establish a local online training method and show how update timing, noise structure, and precision affect generative thermodynamic computing.

Momentum

Related topics

Latest papers 11