Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386002476> ?p ?o ?g. }
- W4386002476 endingPage "119546" @default.
- W4386002476 startingPage "119546" @default.
- W4386002476 abstract "Recent research has shown the significant performance of stochastic gradient descent (SGD) coupled with a momentum trick in solving convex empirical risk minimization (ERM) problems. However, most machine learning problems are nonconvex. An inertial accelerated Prox-SVRG (IAPSVRG) algorithm is proposed to minimize ERM problems with no convexity assumption by incorporating Nesterov's momentum trick into the stochastic variance reduction gradient (SVRG). Certain convergence properties are established for the subsequence are generated by the IAPSVRG algorithm using the supermartingale convergence theorem. Building on the powerful Kurdyka-Łojasiewicz (KL) property, it is shown that each bounded sequence generated by the IAPSVRG algorithm converges globally to a critical point of the objective function if an appropriate threshold of the inertial coefficient is provided. A regularized nonlinear least squares is used to check the effectiveness of the proposed method in terms of classification, convergence, and sensitivity to the choice of the momentum parameter. The experimental results show that the testing accuracy of the proposed algorithm on each of the four selected datasets exceeds at least half that of the other four compared algorithms. Furthermore, the proposed algorithm is less sensitive to the choice of the momentum parameter within a certain threshold compared to the four compared algorithms." @default.
- W4386002476 created "2023-08-20" @default.
- W4386002476 creator A5054067811 @default.
- W4386002476 creator A5062313253 @default.
- W4386002476 creator A5063168172 @default.
- W4386002476 date "2023-11-01" @default.
- W4386002476 modified "2023-10-13" @default.
- W4386002476 title "Nonconvex optimization with inertial proximal stochastic variance reduction gradient" @default.
- W4386002476 cites W1849979240 @default.
- W4386002476 cites W1987083649 @default.
- W4386002476 cites W2006533623 @default.
- W4386002476 cites W2024484010 @default.
- W4386002476 cites W2027982384 @default.
- W4386002476 cites W2047152541 @default.
- W4386002476 cites W2074682976 @default.
- W4386002476 cites W2100556411 @default.
- W4386002476 cites W2107861471 @default.
- W4386002476 cites W2129732816 @default.
- W4386002476 cites W2774820752 @default.
- W4386002476 cites W2901838001 @default.
- W4386002476 cites W2913966198 @default.
- W4386002476 cites W2916621068 @default.
- W4386002476 cites W2963190258 @default.
- W4386002476 cites W3074070670 @default.
- W4386002476 cites W3084718985 @default.
- W4386002476 cites W3094257649 @default.
- W4386002476 cites W3131341170 @default.
- W4386002476 cites W3168954534 @default.
- W4386002476 cites W3183827394 @default.
- W4386002476 cites W3191899281 @default.
- W4386002476 cites W4205203494 @default.
- W4386002476 cites W4283750944 @default.
- W4386002476 cites W4296472732 @default.
- W4386002476 cites W4309746937 @default.
- W4386002476 cites W4312109969 @default.
- W4386002476 cites W4315780867 @default.
- W4386002476 doi "https://doi.org/10.1016/j.ins.2023.119546" @default.
- W4386002476 hasPublicationYear "2023" @default.
- W4386002476 type Work @default.
- W4386002476 citedByCount "0" @default.
- W4386002476 crossrefType "journal-article" @default.
- W4386002476 hasAuthorship W4386002476A5054067811 @default.
- W4386002476 hasAuthorship W4386002476A5062313253 @default.
- W4386002476 hasAuthorship W4386002476A5063168172 @default.
- W4386002476 hasConcept C10138342 @default.
- W4386002476 hasConcept C105795698 @default.
- W4386002476 hasConcept C106159729 @default.
- W4386002476 hasConcept C112680207 @default.
- W4386002476 hasConcept C11413529 @default.
- W4386002476 hasConcept C126255220 @default.
- W4386002476 hasConcept C134306372 @default.
- W4386002476 hasConcept C145446738 @default.
- W4386002476 hasConcept C154945302 @default.
- W4386002476 hasConcept C162324750 @default.
- W4386002476 hasConcept C189237950 @default.
- W4386002476 hasConcept C19499675 @default.
- W4386002476 hasConcept C206688291 @default.
- W4386002476 hasConcept C2524010 @default.
- W4386002476 hasConcept C26517878 @default.
- W4386002476 hasConcept C2777303404 @default.
- W4386002476 hasConcept C28826006 @default.
- W4386002476 hasConcept C33923547 @default.
- W4386002476 hasConcept C34388435 @default.
- W4386002476 hasConcept C38652104 @default.
- W4386002476 hasConcept C41008148 @default.
- W4386002476 hasConcept C50522688 @default.
- W4386002476 hasConcept C50644808 @default.
- W4386002476 hasConcept C55479107 @default.
- W4386002476 hasConcept C60718061 @default.
- W4386002476 hasConcept C62644790 @default.
- W4386002476 hasConcept C72134830 @default.
- W4386002476 hasConceptScore W4386002476C10138342 @default.
- W4386002476 hasConceptScore W4386002476C105795698 @default.
- W4386002476 hasConceptScore W4386002476C106159729 @default.
- W4386002476 hasConceptScore W4386002476C112680207 @default.
- W4386002476 hasConceptScore W4386002476C11413529 @default.
- W4386002476 hasConceptScore W4386002476C126255220 @default.
- W4386002476 hasConceptScore W4386002476C134306372 @default.
- W4386002476 hasConceptScore W4386002476C145446738 @default.
- W4386002476 hasConceptScore W4386002476C154945302 @default.
- W4386002476 hasConceptScore W4386002476C162324750 @default.
- W4386002476 hasConceptScore W4386002476C189237950 @default.
- W4386002476 hasConceptScore W4386002476C19499675 @default.
- W4386002476 hasConceptScore W4386002476C206688291 @default.
- W4386002476 hasConceptScore W4386002476C2524010 @default.
- W4386002476 hasConceptScore W4386002476C26517878 @default.
- W4386002476 hasConceptScore W4386002476C2777303404 @default.
- W4386002476 hasConceptScore W4386002476C28826006 @default.
- W4386002476 hasConceptScore W4386002476C33923547 @default.
- W4386002476 hasConceptScore W4386002476C34388435 @default.
- W4386002476 hasConceptScore W4386002476C38652104 @default.
- W4386002476 hasConceptScore W4386002476C41008148 @default.
- W4386002476 hasConceptScore W4386002476C50522688 @default.
- W4386002476 hasConceptScore W4386002476C50644808 @default.
- W4386002476 hasConceptScore W4386002476C55479107 @default.
- W4386002476 hasConceptScore W4386002476C60718061 @default.
- W4386002476 hasConceptScore W4386002476C62644790 @default.
- W4386002476 hasConceptScore W4386002476C72134830 @default.