English
Related papers

Related papers: Equilibrium Propagation Without Limits

200 papers

We describe expectation propagation for approximate inference in dynamic Bayesian networks as a natural extension of Pearl s exact belief propagation.Expectation propagation IS a greedy algorithm, converges IN many practical cases, but NOT…

Artificial Intelligence · Computer Science 2013-01-07 Tom Heskes , Onno Zoeter

Expectation propagation (EP) is a family of algorithms for performing approximate inference in probabilistic models. The updates of EP involve the evaluation of moments -- expectations of certain functions -- which can be estimated from…

Machine Learning · Statistics 2024-10-30 Jonathan So , Richard E. Turner

The smoothing distribution of dynamic probit models with Gaussian state dynamics was recently proved to belong to the unified skew-normal family. Although this is computationally tractable in small-to-moderate settings, it may become…

Computation · Statistics 2023-09-06 Niccolò Anceschi , Augusto Fasano , Giovanni Rebaudo

Energy-based learning algorithms are alternatives to backpropagation and are well-suited to distributed implementations in analog electronic devices. However, a rigorous theory of convergence is lacking. We make a first step in this…

Optimization and Control · Mathematics 2026-01-28 Anne-Men Huijzer , Thomas Chaffey , Bart Besselink , Henk J. van Waarde

We investigate the problem of approximate Bayesian inference for a general class of observation models by means of the expectation propagation (EP) framework for large systems under some statistical assumptions. Our approach tries to…

Information Theory · Computer Science 2016-08-24 Burak Çakmak , Manfred Opper , Bernard H. Fleury , Ole Winther

Activity difference based learning algorithms-such as contrastive Hebbian learning and equilibrium propagation-have been proposed as biologically plausible alternatives to error back-propagation. However, on traditional digital chips these…

Machine Learning · Computer Science 2023-06-08 Rasmus Høier , D. Staudt , Christopher Zach

Local learning, which trains a network through layer-wise local targets and losses, has been studied as an alternative to backpropagation (BP) in neural computation. However, its algorithms often become more complex or require additional…

Machine Learning · Computer Science 2025-05-22 Satoki Ishikawa , Rio Yokota , Ryo Karakida

Many models of interest in the natural and social sciences have no closed-form likelihood function, which means that they cannot be treated using the usual techniques of statistical inference. In the case where such models can be…

Computation · Statistics 2012-07-19 Simon Barthelmé , Nicolas Chopin

Memristor-based in-memory computing has emerged as a promising paradigm to overcome the constraints of the von Neumann bottleneck and the memory wall by enabling fully parallelisable and energy-efficient vector-matrix multiplications. We…

Machine Learning · Computer Science 2026-02-18 Michael Döll , Andreas Müller , Bernd Ulmann

This paper introduces new parameterizations of equilibrium neural networks, i.e. networks defined by implicit equations. This model class includes standard multilayer and residual networks as special cases. The new parameterization admits a…

Machine Learning · Computer Science 2020-10-06 Max Revay , Ruigang Wang , Ian R. Manchester

Gibbs-ERM learning is a natural idealized model of learning with stochastic optimization algorithms (such as Stochastic Gradient Langevin Dynamics and ---to some extent--- Stochastic Gradient Descent), while it also arises in other…

Machine Learning · Computer Science 2019-02-06 Ilja Kuzborskij , Nicolò Cesa-Bianchi , Csaba Szepesvári

This paper describes an expectation propagation (EP) method for multi-class classification with Gaussian processes that scales well to very large datasets. In such a method the estimate of the log-marginal-likelihood involves a sum across…

Machine Learning · Statistics 2017-06-23 Carlos Villacampa-Calvo , Daniel Hernández-Lobato

We present a new framework for analysing the Expectation Maximization (EM) algorithm. Drawing on recent advances in the theory of gradient flows over Euclidean-Wasserstein spaces, we extend techniques from alternating minimization in…

Machine Learning · Statistics 2025-11-21 Rocco Caprio , Adam M Johansen

On the basis of the general form for the energy needed to adapt the connection strengths of a network in which learning takes place, a local learning rule is found for the changes of the weights. This biologically realizable learning rule…

Disordered Systems and Neural Networks · Physics 2009-10-31 M. Heerema , W. A. van Leeuwen

We formulate natural gradient variational inference (VI), expectation propagation (EP), and posterior linearisation (PL) as extensions of Newton's method for optimising the parameters of a Bayesian posterior distribution. This viewpoint…

Machine Learning · Statistics 2022-12-07 William J. Wilkinson , Simo Särkkä , Arno Solin

Bayesian binary regression is a prosperous area of research due to the computational challenges encountered by currently available methods either for high-dimensional settings or large datasets, or both. In the present work, we focus on the…

Computation · Statistics 2023-09-06 Augusto Fasano , Niccolò Anceschi , Beatrice Franzolini , Giovanni Rebaudo

We propose a method for extending the technique of equilibrium propagation for estimating gradients in fixed-point neural networks to the more general setting of directed, time-varying neural networks by modeling them as electrical…

Machine Learning · Computer Science 2021-03-11 Jack Kendall

Equilibrium propagation has been proposed as a biologically plausible alternative to the backpropagation algorithm. The local nature of gradient computations, combined with the use of convergent RNNs to reach equilibrium states, make this…

Neural and Evolutionary Computing · Computer Science 2026-03-19 Sankar Vinayak Elayedam , Gopalakrishnan Srinivasan

We show that a particular form of target propagation, i.e., relying on learned inverses of each layer, which is differential, i.e., where the target is a small perturbation of the forward propagation, gives rise to an update rule which…

Machine Learning · Computer Science 2020-08-19 Yoshua Bengio

Dependency networks (Heckerman et al., 2000) provide a flexible framework for modeling complex systems with many variables by combining independently learned local conditional distributions through pseudo-Gibbs sampling. Despite their…

Machine Learning · Computer Science 2026-04-02 Kazuya Takabatake , Shotaro Akaho