English
Related papers

Related papers: Quantum Equilibrium Propagation: Gradient-Descent …

200 papers

A growing number of applications in particle physics and beyond use neural networks as unbinned likelihood ratio estimators applied to real or simulated data. Precision requirements on the inference tasks demand a high-level of stability…

High Energy Physics - Phenomenology · Physics 2025-03-04 G. Bruno De Luca , Benjamin Nachman , Eva Silverstein , Henry Zheng

Equilibrium propagation (EP) is a biologically plausible alternative to backpropagation for training neural networks. However, existing EP models use a uniform scalar time step dt, which corresponds biologically to a membrane time constant…

Machine Learning · Computer Science 2026-03-05 Yoshimasa Kubo , Suhani Pragnesh Modi , Smit Patel

Expectation Propagation (EP) provides a framework for approximate inference. When the model under consideration is over a latent Gaussian field, with the approximation being Gaussian, we show how these approximations can systematically be…

Machine Learning · Statistics 2013-10-28 Manfred Opper , Ulrich Paquet , Ole Winther

We employ the influence functional technique to trace out the photonic contribution from full quantum electrodynamics. The reduced density matrix propagator for the spinor field is then constructed. We discuss the role of time-dependent…

High Energy Physics - Theory · Physics 2009-10-30 C. Anastopoulos , A. Zoupas

We develop a framework to test the Equivalence Principle (EP) under conditions where the quantum aspects of nature cannot be neglected, specifically in the context of interference phenomena with unstable particles. We derive the…

General Relativity and Quantum Cosmology · Physics 2013-06-25 Y. Bonder , E. Fischbach , H. Hernandez-Coronado , D. E. Krause , Z. Rohrbach , D. Sudarsky

In general, it is important to identify what is the informational resource for quantum tasks. Quantum energy teleportation (QET) is a quantum task, which attains energy transfer in an operational meaning by local operations and classical…

Quantum Physics · Physics 2015-04-09 Jose Trevison , Masahiro Hotta

We introduce a robust, error-tolerant adaptive training algorithm for generalized learning paradigms in high-dimensional superposed quantum networks, or \emph{adaptive quantum networks}. The formalized procedure applies standard…

Neurons and Cognition · Quantitative Biology 2015-05-13 Christopher Altman , Romàn R. Zapatrin

We develop the theory of Energy Conserving Descent (ECD) and introduce ECDSep, a gradient-based optimization algorithm able to tackle convex and non-convex optimization problems. The method is based on the novel ECD framework of…

Machine Learning · Computer Science 2023-06-02 G. Bruno De Luca , Alice Gatti , Eva Silverstein

Quantum circuit partitioning (QCP) is a hybrid quantum-classical approach that aims to simulate large quantum systems on smaller quantum computers. A quantum computation is divided into smaller subsystems and results of measurements on…

Quantum Physics · Physics 2024-09-20 Stian Bilek

We present a Machine Learning approach to solve electronic quantum transport equations of one-dimensional nanostructures. The transmission coefficients of disordered systems were computed to provide training and test datasets to the…

Mesoscale and Nanoscale Physics · Physics 2015-06-18 Alejandro Lopez-Bezanilla , O. Anatole von Lilienfeld

Power efficiency is plateauing in the standard digital electronics realm such that novel hardware, models, and algorithms are needed to reduce the costs of AI training. The combination of energy-based analog circuits and the Equilibrium…

Machine Learning · Computer Science 2024-09-06 Timothy Nest , Maxence Ernoult

Physical learning machines, be they classical or quantum, are necessarily dissipative systems. The rate of energy dissipation decreases as the learning error rate decreases linking thermodynamic efficiency and learning efficiency. In the…

Quantum Physics · Physics 2023-05-16 G J Milburn

Exponential family distributions are highly useful in machine learning since their calculation can be performed efficiently through natural parameters. The exponential family has recently been extended to the t-exponential family, which…

Machine Learning · Statistics 2017-05-30 Futoshi Futami , Issei Sato , Masashi Sugiyama

In the context of signal detection in the presence of an unknown time-varying channel parameter, receivers based on the Expectation Propagation (EP) framework appear to be very promising. EP is a message-passing algorithm based on factor…

Signal Processing · Electrical Eng. & Systems 2024-04-09 Elisa Conti , Armando Vannucci , Amina Piemontese , Giulio Colavolpe

Quantum Machine Learning is an emerging sub-field in machine learning where one of the goals is to perform pattern recognition tasks by encoding data into quantum states. This extension from classical to quantum domain has been made…

Quantum Physics · Physics 2023-04-18 Ankit Kulshrestha , Xiaoyuan Liu , Hayato Ushijima-Mwesigwa , Ilya Safro

In this work, we extend the Equilibrium Propagation framework to skew-gradient systems and show an equivalence between deep Energy-Based Models and Hamiltonian neural networks. We focus on networks of diffusively coupled Fitzhugh-Nagumo…

Machine Learning · Computer Science 2026-05-22 Jack Kendall

The Einstein Equivalence Principle (EEP), stating that all laws of physics take their special-relativistic form in any local inertial (classical) reference frame, lies at the core of general relativity. Because of its fundamental status,…

Quantum Physics · Physics 2023-06-23 Flaminia Giacomini , Časlav Brukner

We present an accurate numerical algorithm, called quantum belief propagation (QBP), for simulation of one-dimensional quantum systems at non-zero temperature. The algorithm exploits the fact that quantum effects are short-range in these…

Strongly Correlated Electrons · Physics 2009-11-13 M. B. Hastings

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

Quantum machine learning is a promising field for efficiently learning features of a dataset to perform a specified task, such as classification. Interval bound propagation (IBP) is a popular certified training method in classical machine…

Quantum Physics · Physics 2026-05-04 Emma Andrews , Nahyeon Kim , Prabhat Mishra