FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951878358> ?p ?o ?g. }

• W2951878358 abstract "We introduce a novel algorithm for solving learning problems where both the loss function and the regularizer are non-convex but belong to the class of difference of convex (DC) functions. Our contribution is a new general purpose proximal Newton algorithm that is able to deal with such a situation. The algorithm consists in obtaining a descent direction from an approximation of the loss function and then in performing a line search to ensure sufficient descent. A theoretical analysis is provided showing that the iterates of the proposed algorithm {admit} as limit points stationary points of the DC objective function. Numerical experiments show that our approach is more efficient than current state of the art for a problem with a convex loss functions and non-convex regularizer. We have also illustrated the benefit of our algorithm in high-dimensional transductive learning problem where both loss function and regularizers are non-convex." @default.
• W2951878358 created "2019-06-27" @default.
• W2951878358 creator A5003774172 @default.
• W2951878358 creator A5031137438 @default.
• W2951878358 creator A5051249358 @default.
• W2951878358 date "2015-07-02" @default.
• W2951878358 modified "2023-09-27" @default.
• W2951878358 title "DC Proximal Newton for Non-Convex Optimization Problems" @default.
• W2951878358 cites W1592941960 @default.
• W2951878358 cites W1826065584 @default.
• W2951878358 cites W1967138577 @default.
• W2951878358 cites W1968694834 @default.
• W2951878358 cites W1986931325 @default.
• W2951878358 cites W1990494141 @default.
• W2951878358 cites W1994720006 @default.
• W2951878358 cites W2020925091 @default.
• W2951878358 cites W2027982384 @default.
• W2951878358 cites W2050834445 @default.
• W2951878358 cites W2051664786 @default.
• W2951878358 cites W2053386824 @default.
• W2951878358 cites W2069390315 @default.
• W2951878358 cites W2074682976 @default.
• W2951878358 cites W2100556411 @default.
• W2951878358 cites W2103215959 @default.
• W2951878358 cites W2107861471 @default.
• W2951878358 cites W2109449402 @default.
• W2951878358 cites W2112202695 @default.
• W2951878358 cites W2124940450 @default.
• W2951878358 cites W2129732816 @default.
• W2951878358 cites W2135046866 @default.
• W2951878358 cites W2137911812 @default.
• W2951878358 cites W2138428793 @default.
• W2951878358 cites W2142114717 @default.
• W2951878358 cites W2142694817 @default.
• W2951878358 cites W2153413094 @default.
• W2951878358 cites W2154881938 @default.
• W2951878358 cites W2162152253 @default.
• W2951878358 cites W2162361955 @default.
• W2951878358 cites W2166956514 @default.
• W2951878358 cites W2169067611 @default.
• W2951878358 cites W2171413647 @default.
• W2951878358 cites W2205688503 @default.
• W2951878358 cites W2340859457 @default.
• W2951878358 cites W2625093932 @default.
• W2951878358 cites W2798909945 @default.
• W2951878358 cites W2950933264 @default.
• W2951878358 cites W2951715301 @default.
• W2951878358 cites W2963636509 @default.
• W2951878358 cites W33214042 @default.
• W2951878358 hasPublicationYear "2015" @default.
• W2951878358 type Work @default.
• W2951878358 sameAs 2951878358 @default.
• W2951878358 citedByCount "2" @default.
• W2951878358 countsByYear W29518783582015 @default.
• W2951878358 countsByYear W29518783582016 @default.
• W2951878358 crossrefType "posted-content" @default.
• W2951878358 hasAuthorship W2951878358A5003774172 @default.
• W2951878358 hasAuthorship W2951878358A5031137438 @default.
• W2951878358 hasAuthorship W2951878358A5051249358 @default.
• W2951878358 hasConcept C10494615 @default.
• W2951878358 hasConcept C111110010 @default.
• W2951878358 hasConcept C112680207 @default.
• W2951878358 hasConcept C11413529 @default.
• W2951878358 hasConcept C116149140 @default.
• W2951878358 hasConcept C118888059 @default.
• W2951878358 hasConcept C12108790 @default.
• W2951878358 hasConcept C126255220 @default.
• W2951878358 hasConcept C134306372 @default.
• W2951878358 hasConcept C14036430 @default.
• W2951878358 hasConcept C140479938 @default.
• W2951878358 hasConcept C145446738 @default.
• W2951878358 hasConcept C151201525 @default.
• W2951878358 hasConcept C153258448 @default.
• W2951878358 hasConcept C154945302 @default.
• W2951878358 hasConcept C157972887 @default.
• W2951878358 hasConcept C178635117 @default.
• W2951878358 hasConcept C2524010 @default.
• W2951878358 hasConcept C33923547 @default.
• W2951878358 hasConcept C38652104 @default.
• W2951878358 hasConcept C41008148 @default.
• W2951878358 hasConcept C50644808 @default.
• W2951878358 hasConcept C50862404 @default.
• W2951878358 hasConcept C78458016 @default.
• W2951878358 hasConcept C85522705 @default.
• W2951878358 hasConcept C86803240 @default.
• W2951878358 hasConceptScore W2951878358C10494615 @default.
• W2951878358 hasConceptScore W2951878358C111110010 @default.
• W2951878358 hasConceptScore W2951878358C112680207 @default.
• W2951878358 hasConceptScore W2951878358C11413529 @default.
• W2951878358 hasConceptScore W2951878358C116149140 @default.
• W2951878358 hasConceptScore W2951878358C118888059 @default.
• W2951878358 hasConceptScore W2951878358C12108790 @default.
• W2951878358 hasConceptScore W2951878358C126255220 @default.
• W2951878358 hasConceptScore W2951878358C134306372 @default.
• W2951878358 hasConceptScore W2951878358C14036430 @default.
• W2951878358 hasConceptScore W2951878358C140479938 @default.
• W2951878358 hasConceptScore W2951878358C145446738 @default.
• W2951878358 hasConceptScore W2951878358C151201525 @default.
• W2951878358 hasConceptScore W2951878358C153258448 @default.
• W2951878358 hasConceptScore W2951878358C154945302 @default.

• next