English
Related papers

Related papers: Symmetric Equilibrium Propagation for Thermodynami…

200 papers

Exponentiated gradient descent (EGD), a biologically motivated optimisation algorithm that respects Dale's law, produces log-normally distributed synaptic weights at convergence, in alignment with experimental observations in neuroscience.…

Machine Learning · Computer Science 2026-05-26 Nishanth Shetty , Madhava Prasath , Chandra Sekhar Seelamantula

The search for ``biologically plausible'' learning algorithms has converged on the idea of representing gradients as activity differences. However, most approaches require a high degree of synchronization (distinct phases during learning)…

Machine Learning · Computer Science 2024-12-03 Rasmus Kjær Høier , Christopher Zach

Brain-like intelligent systems need brain-like learning methods. Equilibrium Propagation (EP) is a biologically plausible learning framework with strong potential for brain-inspired computing hardware. However, existing im-plementations of…

Neural and Evolutionary Computing · Computer Science 2026-05-08 Zhuo Liu , Tao Chen

The biological plausibility of the backpropagation algorithm has long been doubted by neuroscientists. Two major reasons are that neurons would need to send two different types of signal in the forward and backward phases, and that pairs of…

Machine Learning · Computer Science 2018-08-16 Benjamin Scellier , Anirudh Goyal , Jonathan Binas , Thomas Mesnard , Yoshua Bengio

Equilibrium Propagation (EP) is a biologically plausible local learning algorithm initially developed for convergent recurrent neural networks (RNNs), where weight updates rely solely on the connecting neuron states across two phases. The…

Neural and Evolutionary Computing · Computer Science 2024-07-04 Jiaqi Lin , Malyaban Bal , Abhronil Sengupta

Equilibrium Propagation (EP) is a biologically inspired learning algorithm for convergent recurrent neural networks, i.e. RNNs that are fed by a static input x and settle to a steady state. Training convergent RNNs consists in adjusting the…

Machine Learning · Computer Science 2019-06-03 Maxence Ernoult , Julie Grollier , Damien Querlioz , Yoshua Bengio , Benjamin Scellier

Equilibrium propagation is a recently introduced method to use and train artificial neural networks in which the network is at the minimum (more generally extremum) of an energy functional. Equilibrium propagation has shown good performance…

Quantum Physics · Physics 2024-12-03 Serge Massar , Bortolo Matteo Mognetti

Diffusion models are extensively used for modeling image priors for inverse problems. We introduce \emph{Diff-Unfolding}, a principled framework for learning posterior score functions of \emph{conditional diffusion models} by explicitly…

Image and Video Processing · Electrical Eng. & Systems 2025-05-22 Yuanhao Wang , Shirin Shoushtari , Ulugbek S. Kamilov

Score-based diffusion models have recently been extended to infinite-dimensional function spaces, with uses such as inverse problems arising from partial differential equations. In the Bayesian formulation of inverse problems, the aim is to…

Machine Learning · Computer Science 2026-05-12 Elizabeth L. Baker , Alexander Denker , Jes Frellsen

Machine learning is a powerful method of extracting meaning from data; unfortunately, current digital hardware is extremely energy-intensive. There is interest in an alternative analog computing implementation that could match the…

Machine Learning · Computer Science 2026-02-17 Jonathan Lin , Aman Desai , Frank Barrows , Francesco Caravelli

Equilibrium Propagation (EP) is a biologically inspired alternative algorithm to backpropagation (BP) for training neural networks. It applies to RNNs fed by a static input x that settle to a steady state, such as Hopfield networks. EP is…

Neural and Evolutionary Computing · Computer Science 2020-05-11 Maxence Ernoult , Julie Grollier , Damien Querlioz , Yoshua Bengio , Benjamin Scellier

This work introduces a sampling method capable of solving Bayesian inverse problems in function space. It does not assume the log-concavity of the likelihood, meaning that it is compatible with nonlinear inverse problems. The method…

Machine Learning · Statistics 2024-05-27 Lorenzo Baldassari , Ali Siahkoohi , Josselin Garnier , Knut Solna , Maarten V. de Hoop

The rapid growth of deep neural networks (DNNs) has brought increasing attention to their energy use during training and inference. Here, we establish the thermodynamic bounds on energy consumption in quasi-static analog DNNs by mapping…

Statistical Mechanics · Physics 2025-12-09 Alexei V. Tkachenko

With the prosperity of mobile devices, the distributed learning approach enabling model training with decentralized data has attracted wide research. However, the lack of training capability for edge devices significantly limits the energy…

Machine Learning · Computer Science 2021-05-14 Ziyang Hong , C. Patrick Yue

This paper proposes a novel diffusion-based posterior sampling method within a plug-and-play (PnP) framework. Our approach constructs a probability transport from an easy-to-sample terminal distribution to the target posterior, using a…

Machine Learning · Statistics 2025-12-10 Jinyuan Chang , Chenguang Duan , Yuling Jiao , Ruoxuan Li , Jerry Zhijian Yang , Cheng Yuan

We fix a fundamental issue in the stochastic extragradient method by providing a new sampling strategy that is motivated by approximating implicit updates. Since the existing stochastic extragradient algorithm, called Mirror-Prox, of…

Optimization and Control · Mathematics 2021-02-22 Konstantin Mishchenko , Dmitry Kovalev , Egor Shulgin , Peter Richtárik , Yura Malitsky

Diffusion models are gaining widespread use in cutting-edge image, video, and audio generation. Score-based diffusion models stand out among these methods, necessitating the estimation of score function of the input data distribution. In…

Machine Learning · Computer Science 2024-05-24 Fangzhao Zhang , Mert Pilanci

We introduce novel communication strategies in synchronous distributed Deep Learning consisting of decentralized gradient reduction orchestration and computational graph-aware grouping of gradient tensors. These new techniques produce an…

Binary Neural Networks (BNNs), which constrain both weights and activations to binary values, offer substantial reductions in computational complexity, memory footprint, and energy consumption. These advantages make them particularly well…

Machine Learning · Computer Science 2026-02-18 Luca Colombo , Fabrizio Pittorino , Daniele Zambon , Carlo Baldassi , Manuel Roveri , Cesare Alippi

Equilibrium propagation (EP) is an alternative to backpropagation (BP) that allows the training of deep neural networks with local learning rules. It thus provides a compelling framework for training neuromorphic systems and understanding…

Machine Learning · Computer Science 2022-09-02 Axel Laborieux , Friedemann Zenke