Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896346037> ?p ?o ?g. }
- W2896346037 abstract "We develop new perturbation techniques for conducting convergence analysis of various first-order algorithms for a class of nonsmooth optimization problems. We consider the iteration scheme of an algorithm to construct a perturbed stationary point set-valued map, and define the perturbing parameter by the difference of two consecutive iterates. Then, we show that the calmness condition of the induced set-valued map, together with a local version of the proper separation of stationary value condition, is a sufficient condition to ensure the linear convergence of the algorithm. The equivalence of the calmness condition to the one for the canonically perturbed stationary point set-valued map is proved, and this equivalence allows us to derive some sufficient conditions for calmness by using some recent developments in variational analysis. These sufficient conditions are different from existing results (especially, those error-bound-based ones) in that they can be easily verified for many concrete application models. Our analysis is focused on the fundamental proximal gradient (PG) method, and it enables us to show that any accumulation of the sequence generated by the PG method must be a stationary point in terms of the proximal subdifferential, instead of the limiting subdifferential. This result finds the surprising fact that the solution quality found by the PG method is in general superior. Our analysis also leads to some improvement for the linear convergence results of the PG method in the convex case. The new perturbation technique can be conveniently used to derive linear rate convergence of a number of other first-order methods including the well-known alternating direction method of multipliers and primal-dual hybrid gradient method, under mild assumptions." @default.
- W2896346037 created "2018-10-26" @default.
- W2896346037 creator A5014555178 @default.
- W2896346037 creator A5055174519 @default.
- W2896346037 creator A5067148719 @default.
- W2896346037 creator A5077189077 @default.
- W2896346037 creator A5077548287 @default.
- W2896346037 date "2018-10-23" @default.
- W2896346037 modified "2023-09-30" @default.
- W2896346037 title "Perturbation techniques for convergence analysis of proximal gradient method and other first-order algorithms via variational analysis" @default.
- W2896346037 cites W1235853611 @default.
- W2896346037 cites W1495241813 @default.
- W2896346037 cites W1568288633 @default.
- W2896346037 cites W1965125844 @default.
- W2896346037 cites W1967138577 @default.
- W2896346037 cites W1970298676 @default.
- W2896346037 cites W1982325686 @default.
- W2896346037 cites W1984273780 @default.
- W2896346037 cites W1993647205 @default.
- W2896346037 cites W1998576973 @default.
- W2896346037 cites W2004160833 @default.
- W2896346037 cites W2014715559 @default.
- W2896346037 cites W2021361347 @default.
- W2896346037 cites W2021548137 @default.
- W2896346037 cites W2027982384 @default.
- W2896346037 cites W2039050532 @default.
- W2896346037 cites W2063173399 @default.
- W2896346037 cites W2068357778 @default.
- W2896346037 cites W2074682976 @default.
- W2896346037 cites W2093417350 @default.
- W2896346037 cites W2094683072 @default.
- W2896346037 cites W2097287227 @default.
- W2896346037 cites W2100556411 @default.
- W2896346037 cites W2101868363 @default.
- W2896346037 cites W2127447444 @default.
- W2896346037 cites W2131815933 @default.
- W2896346037 cites W2145085734 @default.
- W2896346037 cites W2153565720 @default.
- W2896346037 cites W2161227280 @default.
- W2896346037 cites W2278798990 @default.
- W2896346037 cites W2294426261 @default.
- W2896346037 cites W2496276084 @default.
- W2896346037 cites W2531478387 @default.
- W2896346037 cites W2533581970 @default.
- W2896346037 cites W2557283755 @default.
- W2896346037 cites W2919115771 @default.
- W2896346037 cites W2952975724 @default.
- W2896346037 cites W2963118312 @default.
- W2896346037 cites W2963254198 @default.
- W2896346037 cites W3100208521 @default.
- W2896346037 cites W3100765371 @default.
- W2896346037 cites W3157341860 @default.
- W2896346037 doi "https://doi.org/10.48550/arxiv.1810.10051" @default.
- W2896346037 hasPublicationYear "2018" @default.
- W2896346037 type Work @default.
- W2896346037 sameAs 2896346037 @default.
- W2896346037 citedByCount "5" @default.
- W2896346037 countsByYear W28963460372018 @default.
- W2896346037 countsByYear W28963460372019 @default.
- W2896346037 countsByYear W28963460372020 @default.
- W2896346037 crossrefType "posted-content" @default.
- W2896346037 hasAuthorship W2896346037A5014555178 @default.
- W2896346037 hasAuthorship W2896346037A5055174519 @default.
- W2896346037 hasAuthorship W2896346037A5067148719 @default.
- W2896346037 hasAuthorship W2896346037A5077189077 @default.
- W2896346037 hasAuthorship W2896346037A5077548287 @default.
- W2896346037 hasBestOaLocation W28963460371 @default.
- W2896346037 hasConcept C112680207 @default.
- W2896346037 hasConcept C11413529 @default.
- W2896346037 hasConcept C118552586 @default.
- W2896346037 hasConcept C118615104 @default.
- W2896346037 hasConcept C121332964 @default.
- W2896346037 hasConcept C126255220 @default.
- W2896346037 hasConcept C127162648 @default.
- W2896346037 hasConcept C134306372 @default.
- W2896346037 hasConcept C140479938 @default.
- W2896346037 hasConcept C15744967 @default.
- W2896346037 hasConcept C157972887 @default.
- W2896346037 hasConcept C162324750 @default.
- W2896346037 hasConcept C177918212 @default.
- W2896346037 hasConcept C189237950 @default.
- W2896346037 hasConcept C200661725 @default.
- W2896346037 hasConcept C2524010 @default.
- W2896346037 hasConcept C2777303404 @default.
- W2896346037 hasConcept C2778712213 @default.
- W2896346037 hasConcept C2780069185 @default.
- W2896346037 hasConcept C28826006 @default.
- W2896346037 hasConcept C31258907 @default.
- W2896346037 hasConcept C33923547 @default.
- W2896346037 hasConcept C41008148 @default.
- W2896346037 hasConcept C50522688 @default.
- W2896346037 hasConcept C523394659 @default.
- W2896346037 hasConcept C57869625 @default.
- W2896346037 hasConcept C62520636 @default.
- W2896346037 hasConcept C63548660 @default.
- W2896346037 hasConceptScore W2896346037C112680207 @default.
- W2896346037 hasConceptScore W2896346037C11413529 @default.
- W2896346037 hasConceptScore W2896346037C118552586 @default.
- W2896346037 hasConceptScore W2896346037C118615104 @default.
- W2896346037 hasConceptScore W2896346037C121332964 @default.