DisSAGD: A Distributed Parameter Update Scheme Based on Variance Reduction [PDF]
Sensors, 2021 Machine learning models often converge slowly and are unstable due to the significant variance of random data when using a sample estimate gradient in SGD.
Haijie Pan, Lirong Zheng
doaj +2 more sources
Fast PET reconstruction with variance reduction and prior-aware preconditioning [PDF]
Frontiers in Nuclear MedicineWe investigated subset-based optimization methods for positron emission tomography (PET) image reconstruction incorporating a regularizing prior. PET reconstruction methods that use a prior, such as the relative difference prior (RDP), are of particular ...
Matthias J. Ehrhardt +2 more
doaj +2 more sources
Accelerated Stochastic Variance Reduction Gradient Algorithms for Robust Subspace Clustering [PDF]
SensorsRobust face clustering enjoys a wide range of applications for gate passes, surveillance systems and security analysis in embedded sensors. Nevertheless, existing algorithms have limitations in finding accurate clusters when data contain noise (e.g ...
Hongying Liu +5 more
doaj +2 more sources
Optimization of variance reduction techniques used in EGSnrc Monte Carlo Codes [PDF]
Journal of Medical Physics, 2018 Monte Carlo (MC) simulations are often used in calculations of radiation transport to enable accurate prediction of radiation-dose, even though the computation is relatively time-consuming.
Sangeetha Shanmugasundaram +1 more
doaj +2 more sources
EFFECT OF THE UNIFORM FISSION SOURCE METHOD ON LOCAL POWER VARIANCE IN FULL CORE SERPENT CALCULATION [PDF]
EPJ Web of Conferences, 2021 One of challenges of the Monte Carlo full core simulations is to obtain acceptable statistical variance of local parameters throughout the whole reactor core at a reasonable computation cost.
Bilodid Yurii, Leppänen Jaakko
doaj +1 more source
IMPLEMENTATION OF MONTE CARLO MOMENT MATCHING METHOD FOR PRICING LOOKBACK FLOATING STRIKE OPTION
Barekeng, 2022 Monte Carlo method was a numerical method that was popular in finance. This method had disadvantages at convergences, so the moment matching was used to improve the efficiency from Monte Carlo method.
Komang Nonik Afsari Dewi +2 more
doaj +1 more source
TOWARDS ZERO-VARIANCE SCHEMES FOR KINETIC MONTE-CARLO SIMULATIONS [PDF]
EPJ Web of Conferences, 2021 The solution of the time-dependent transport problem for neutrons and precursors in a nuclear reactor is hard to treat in a naive Monte-Carlo framework because of the largely different time scales associated to the prompt-fission chains and to the decay ...
Mancusi Davide, Zoia Andrea
doaj +1 more source
ROBUST SIMULATION METHOD OF COMPLEX TECHNICAL TRANSPORT SYSTEMS [PDF]
Transport Problems, 2021 In the optimization of technical systems focused on a specific functional purpose (reliability, safety, and availability) with the use of simulation methods, an important parameter is the digital simulation time of the research subject.
Janusz SZPYTKO, Yorlandys SALGADO DUARTE
doaj +1 more source
Generalizing the Balance Heuristic Estimator in Multiple Importance Sampling
Entropy, 2022 In this paper, we propose a novel and generic family of multiple importance sampling estimators. We first revisit the celebrated balance heuristic estimator, a widely used Monte Carlo technique for the approximation of intractable integrals.
Mateu Sbert, Víctor Elvira
doaj +1 more source
Pilot development: an empirical mixed-method analysis [PDF]
Journal of Defense Analytics and Logistics, 2022 Purpose – Pilot upgrade training is critical to aircraft and passenger safety. This study aims to identify variances in the US Air Force C-130J pilot upgrade training based on geographic location and provide a model to enhance policy that will impact ...
Jonathan Slottje +3 more
doaj +1 more source