LEADER 03753nam 22006855 450 001 9910896179403321 005 20260119145926.0 010 $a981-9767-69-5 024 7 $a10.1007/978-981-97-6769-4 035 $a(MiAaPQ)EBC31702425 035 $a(Au-PeEL)EBL31702425 035 $a(CKB)36271354100041 035 $a(DE-He213)978-981-97-6769-4 035 $a(EXLCZ)9936271354100041 100 $a20241002d2024 u| 0 101 0 $aeng 135 $aurcnu|||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aAdvanced Techniques in Optimization for Machine Learning and Imaging /$fedited by Alessandro Benfenati, Federica Porta, Tatiana Alessandra Bubba, Marco Viola 205 $a1st ed. 2024. 210 1$aSingapore :$cSpringer Nature Singapore :$cImprint: Springer,$d2024. 215 $a1 online resource (173 pages) 225 1 $aSpringer INdAM Series,$x2281-5198 ;$v61 311 08$a981-9767-68-7 320 $aIncludes bibliographical references. 327 $a1.STEMPO dynamic Xray tomography phantom -- 2.On a fixed point continuation method for a convex optimization problem -- 3.Majoration Minimization for Sparse SVMs -- 4.Bilevel learning of regularization models and their discretization for image deblurring and super resolution -- 5.Non Log Concave and Nonsmooth Sampling via Langevin Monte Carlo Algorithms -- 6.On the inexact proximal Gauss-Newton methods for regularized nonlinear least squares problems. 330 $aIn recent years, non-linear optimization has had a crucial role in the development of modern techniques at the interface of machine learning and imaging. The present book is a collection of recent contributions in the field of optimization, either revisiting consolidated ideas to provide formal theoretical guarantees or providing comparative numerical studies for challenging inverse problems in imaging. The work of these papers originated in the INdAM Workshop ?Advanced Techniques in Optimization for Machine learning and Imaging? held in Roma, Italy, on June 20-24, 2022. The covered topics include non-smooth optimisation techniques for model-driven variational regularization, fixed-point continuation algorithms and their theoretical analysis for selection strategies of the regularization parameter for linear inverse problems in imaging, different perspectives on Support Vector Machines trained via Majorization-Minimization methods, generalization of Bayesian statistical frameworks to imaging problems, and creation of benchmark datasets for testing new methods and algorithms. 410 0$aSpringer INdAM Series,$x2281-5198 ;$v61 606 $aMachine learning 606 $aMathematical optimization 606 $aMathematical analysis 606 $aMachine Learning 606 $aOptimization 606 $aAnalysis 606 $aAprenentatge automātic$2thub 606 $aOptimitzaciķ matemātica$2thub 606 $aTeories no lineals$2thub 606 $aProcessament digital d'imatges$2thub 608 $aLlibres electrōnics$2thub 615 0$aMachine learning. 615 0$aMathematical optimization. 615 0$aMathematical analysis. 615 14$aMachine Learning. 615 24$aOptimization. 615 24$aAnalysis. 615 7$aAprenentatge automātic 615 7$aOptimitzaciķ matemātica 615 7$aTeories no lineals 615 7$aProcessament digital d'imatges 676 $a006.6 702 $aBenfenati$b Alessandro 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910896179403321 996 $aAdvanced Techniques in Optimization for Machine Learning and Imaging$94431919 997 $aUNINA