Matches in SemOpenAlex for { <https://semopenalex.org/work/W3089726219> ?p ?o ?g. }
- W3089726219 abstract "Variable metric proximal gradient methods with different metric selections have been widely used in composite optimization. Combining the Barzilai-Borwein (BB) method with a diagonal selection strategy for the metric, the diagonal BB stepsize can keep low per-step computation cost as the scalar BB stepsize and better capture the local geometry of the problem. In this paper, we propose a variable metric mini-batch proximal stochastic recursive gradient algorithm VM-mSRGBB, which updates the metric using a new diagonal BB stepsize. The linear convergence of VM-mSRGBB is established for strongly convex, non-strongly convex and convex functions. Numerical experiments on standard data sets show that VM-mSRGBB is better than or comparable to some variance reduced stochastic gradient methods with best-tuned scalar stepsizes or BB stepsizes. Furthermore, the performance of VM-mSRGBB is superior to some advanced mini-batch proximal stochastic gradient methods." @default.
- W3089726219 created "2020-10-08" @default.
- W3089726219 creator A5009569401 @default.
- W3089726219 creator A5058333923 @default.
- W3089726219 creator A5067535569 @default.
- W3089726219 creator A5090731919 @default.
- W3089726219 date "2020-10-02" @default.
- W3089726219 modified "2023-09-27" @default.
- W3089726219 title "A variable metric mini-batch proximal stochastic recursive gradient algorithm with diagonal Barzilai-Borwein stepsize" @default.
- W3089726219 cites W1497361805 @default.
- W3089726219 cites W1554944419 @default.
- W3089726219 cites W1569098853 @default.
- W3089726219 cites W1994616650 @default.
- W3089726219 cites W2024484010 @default.
- W3089726219 cites W2030161963 @default.
- W3089726219 cites W2047152541 @default.
- W3089726219 cites W2062320580 @default.
- W3089726219 cites W2076605490 @default.
- W3089726219 cites W2100556411 @default.
- W3089726219 cites W2105875671 @default.
- W3089726219 cites W2107438106 @default.
- W3089726219 cites W2135482703 @default.
- W3089726219 cites W2153749284 @default.
- W3089726219 cites W2212417330 @default.
- W3089726219 cites W2217490359 @default.
- W3089726219 cites W2229440883 @default.
- W3089726219 cites W2271321931 @default.
- W3089726219 cites W2514742857 @default.
- W3089726219 cites W2556623528 @default.
- W3089726219 cites W2557283755 @default.
- W3089726219 cites W2745037491 @default.
- W3089726219 cites W2763081248 @default.
- W3089726219 cites W2765352990 @default.
- W3089726219 cites W2804009132 @default.
- W3089726219 cites W2913535645 @default.
- W3089726219 cites W2962677560 @default.
- W3089726219 cites W2962688058 @default.
- W3089726219 cites W2962696654 @default.
- W3089726219 cites W2962897178 @default.
- W3089726219 cites W2963087817 @default.
- W3089726219 cites W2963156201 @default.
- W3089726219 cites W2963248893 @default.
- W3089726219 cites W2963804082 @default.
- W3089726219 cites W2964093568 @default.
- W3089726219 cites W2980725457 @default.
- W3089726219 cites W3008961984 @default.
- W3089726219 cites W3039770199 @default.
- W3089726219 cites W3092439306 @default.
- W3089726219 cites W607505555 @default.
- W3089726219 hasPublicationYear "2020" @default.
- W3089726219 type Work @default.
- W3089726219 sameAs 3089726219 @default.
- W3089726219 citedByCount "2" @default.
- W3089726219 countsByYear W30897262192021 @default.
- W3089726219 crossrefType "posted-content" @default.
- W3089726219 hasAuthorship W3089726219A5009569401 @default.
- W3089726219 hasAuthorship W3089726219A5058333923 @default.
- W3089726219 hasAuthorship W3089726219A5067535569 @default.
- W3089726219 hasAuthorship W3089726219A5090731919 @default.
- W3089726219 hasConcept C112680207 @default.
- W3089726219 hasConcept C11413529 @default.
- W3089726219 hasConcept C115680565 @default.
- W3089726219 hasConcept C126255220 @default.
- W3089726219 hasConcept C130367717 @default.
- W3089726219 hasConcept C134306372 @default.
- W3089726219 hasConcept C162324750 @default.
- W3089726219 hasConcept C176217482 @default.
- W3089726219 hasConcept C198043062 @default.
- W3089726219 hasConcept C21547014 @default.
- W3089726219 hasConcept C2524010 @default.
- W3089726219 hasConcept C2777303404 @default.
- W3089726219 hasConcept C28826006 @default.
- W3089726219 hasConcept C33923547 @default.
- W3089726219 hasConcept C50522688 @default.
- W3089726219 hasConceptScore W3089726219C112680207 @default.
- W3089726219 hasConceptScore W3089726219C11413529 @default.
- W3089726219 hasConceptScore W3089726219C115680565 @default.
- W3089726219 hasConceptScore W3089726219C126255220 @default.
- W3089726219 hasConceptScore W3089726219C130367717 @default.
- W3089726219 hasConceptScore W3089726219C134306372 @default.
- W3089726219 hasConceptScore W3089726219C162324750 @default.
- W3089726219 hasConceptScore W3089726219C176217482 @default.
- W3089726219 hasConceptScore W3089726219C198043062 @default.
- W3089726219 hasConceptScore W3089726219C21547014 @default.
- W3089726219 hasConceptScore W3089726219C2524010 @default.
- W3089726219 hasConceptScore W3089726219C2777303404 @default.
- W3089726219 hasConceptScore W3089726219C28826006 @default.
- W3089726219 hasConceptScore W3089726219C33923547 @default.
- W3089726219 hasConceptScore W3089726219C50522688 @default.
- W3089726219 hasLocation W30897262191 @default.
- W3089726219 hasOpenAccess W3089726219 @default.
- W3089726219 hasPrimaryLocation W30897262191 @default.
- W3089726219 hasRelatedWork W1983212821 @default.
- W3089726219 hasRelatedWork W2045423624 @default.
- W3089726219 hasRelatedWork W2147587978 @default.
- W3089726219 hasRelatedWork W2151471453 @default.
- W3089726219 hasRelatedWork W2329996474 @default.
- W3089726219 hasRelatedWork W2522336029 @default.
- W3089726219 hasRelatedWork W2617742785 @default.
- W3089726219 hasRelatedWork W2669391889 @default.