ON LEAST SQUARES AUTO-TUNING FOR IMAGE CLASSIFICATION USING THE KUZUSHIJI-MNIST DATASET: NUMERICAL EXPERIMENT
Author(s) : HSIN-YU CHEN , KAN-LIN HSIUNG
Abstract
Recently, a novel method, called the “least squares auto-tuningâ€, which can find hyper-parameters in LS problems (that minimize another (true) objective), is proposed [1]. Although nonconvex and cannot be efficiently solved, this problem can be approximately solved using a powerful proximal gradient method to find good hyper-parameters (for LS problems).
Conference Title : 7th International E- conference on Engineering, Technology and Management - ICETM 2022
Conference Date(s) : 11 June, 2022
Place : Online (Via Video Conference)
No fo Author(s) : 2
DOI : 10.15224/ 978-1-63248-194-8-07
Page(s) : 39
Electronic ISBN : 978-1-63248-194-8
Full Paper PDF
Views : 266 | Download(s) : 122
