Results 1 to 10 of about 31,755,712 (367)

A Variational Perspective on Accelerated Methods in Optimization [PDF]

open access: yesProceedings of the National Academy of Sciences of the United States of America, 2016
Accelerated gradient methods play a central role in optimization, achieving optimal rates in many settings. While many generalizations and extensions of Nesterov's original acceleration method have been proposed, it is not yet clear what is the natural ...
Jordan, Michael I.   +2 more
core   +2 more sources

Improved variational methods in statistical data assimilation [PDF]

open access: yesNonlinear Processes in Geophysics, 2015
Data assimilation transfers information from an observed system to a physically based model system with state variables x(t). The observations are typically noisy, the model has errors, and the initial state x(t0) is uncertain: the data assimilation ...
J. Ye   +4 more
doaj   +2 more sources

Variational methods for simulation-based inference [PDF]

open access: yesInternational Conference on Learning Representations, 2022
We present Sequential Neural Variational Inference (SNVI), an approach to perform Bayesian inference in models with intractable likelihoods. SNVI combines likelihood-estimation (or likelihood-ratio-estimation) with variational inference to achieve a ...
Manuel Glöckler   +2 more
semanticscholar   +1 more source

Performance comparison of optimization methods on variational quantum algorithms [PDF]

open access: yesPhysical Review A, 2021
Variational quantum algorithms (VQAs) offer a promising path toward using near-term quantum hardware for applications in academic and industrial research. These algorithms aim to find approximate solutions to quantum problems by optimizing a parametrized
Xavier Bonet-Monroig   +7 more
semanticscholar   +1 more source

Network element methods for linear elasticity

open access: yesComptes Rendus. Mécanique, 2023
We explain how to derive a network element for the linear elasticity problem. After presenting sufficient conditions on the network for the validity of a discrete Korn inequality, we also propose several variations of the presented method and in ...
Coatléven, Julien
doaj   +1 more source

On three-step iterative schemes associated with general quasi-variational inclusions

open access: yesAlexandria Engineering Journal, 2022
In this paper, we investigate new classes of general quasi-variational inclusions. In this regard, we prove that general quasi-variational inclusions and fixed point problems are equivalent.
Muhammad Aslam Noor   +3 more
doaj   +1 more source

Geometry of variational methods: dynamics of closed quantum systems [PDF]

open access: yes, 2020
We present a systematic geometric framework to study closed quantum systems based on suitably chosen variational families. For the purpose of (A) real time evolution, (B) excitation spectra, (C) spectral functions and (D) imaginary time evolution, we ...
L. Hackl   +5 more
semanticscholar   +1 more source

The variational method of moments

open access: yesJournal of the Royal Statistical Society Series B: Statistical Methodology, 2023
Abstract The conditional moment problem is a powerful formulation for describing structural causal parameters in terms of observables, a prominent example being instrumental variable regression. We introduce a very general class of estimators called the variational method of moments (VMM), motivated by a variational minimax reformulation
Bennett, Andrew, Kallus, Nathan
openaire   +2 more sources

Variational Inference: A Review for Statisticians [PDF]

open access: yesarXiv.org, 2016
One of the core problems of modern statistics is to approximate difficult-to-compute probability densities. This problem is especially important in Bayesian statistics, which frames all inference about unknown quantities as a calculation involving the ...
D. Blei, A. Kucukelbir, Jon D. McAuliffe
semanticscholar   +1 more source

Variational Methods in Optical Quantum Machine Learning

open access: yesIEEE Access, 2023
The computing world is rapidly evolving and advancing, with new ground-breaking technologies emerging. Quantum Computing and Quantum Machine Learning have opened up new possibilities, providing unprecedented computational power and problem-solving ...
Marco Simonetti   +2 more
doaj   +1 more source

Home - About - Disclaimer - Privacy