Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286492109> ?p ?o ?g. }
- W4286492109 endingPage "1697" @default.
- W4286492109 startingPage "1668" @default.
- W4286492109 abstract "Making the gradients small is a fundamental optimization problem that has eluded unifying and simple convergence arguments in first-order optimization, so far primarily reserved for other convergence criteria, such as reducing the optimality gap. In particular, while many different potential function-based frameworks covering broad classes of algorithms exist for optimality gap-based convergence guarantees, we are not aware of such general frameworks addressing the gradient norm guarantees. To fill this gap, we introduce a novel potential function-based framework to study the convergence of standard methods for making the gradients small in smooth convex optimization and convex-concave min-max optimization. Our framework is intuitive and provides a lens for viewing algorithms that makes the gradients small as being driven by a trade-off between reducing either the gradient norm or a certain notion of an optimality gap. On the lower bounds side, we discuss tightness of the obtained convergence results for the convex setup and provide a new lower bound for minimizing norm of cocoercive operators that allows us to argue about optimality of methods in the min-max setup." @default.
- W4286492109 created "2022-07-22" @default.
- W4286492109 creator A5047540105 @default.
- W4286492109 creator A5076054793 @default.
- W4286492109 date "2022-07-21" @default.
- W4286492109 modified "2023-10-14" @default.
- W4286492109 title "Potential Function-Based Framework for Minimizing Gradients in Convex and Min-Max Optimization" @default.
- W4286492109 cites W1962121538 @default.
- W4286492109 cites W1967138577 @default.
- W4286492109 cites W1970033879 @default.
- W4286492109 cites W1979896658 @default.
- W4286492109 cites W1986046400 @default.
- W4286492109 cites W2026040627 @default.
- W4286492109 cites W2030161963 @default.
- W4286492109 cites W2043093325 @default.
- W4286492109 cites W2047605837 @default.
- W4286492109 cites W206682702 @default.
- W4286492109 cites W2068357778 @default.
- W4286492109 cites W2069435104 @default.
- W4286492109 cites W2081316950 @default.
- W4286492109 cites W2081985785 @default.
- W4286492109 cites W2082569121 @default.
- W4286492109 cites W2089559088 @default.
- W4286492109 cites W2095030074 @default.
- W4286492109 cites W2114605231 @default.
- W4286492109 cites W2508323711 @default.
- W4286492109 cites W2601574318 @default.
- W4286492109 cites W2606904667 @default.
- W4286492109 cites W2772443375 @default.
- W4286492109 cites W2901838001 @default.
- W4286492109 cites W2951335402 @default.
- W4286492109 cites W2963022670 @default.
- W4286492109 cites W2963385703 @default.
- W4286492109 cites W2963430672 @default.
- W4286492109 cites W2964000362 @default.
- W4286492109 cites W2964093568 @default.
- W4286492109 cites W2964102336 @default.
- W4286492109 cites W2965299328 @default.
- W4286492109 cites W3037153379 @default.
- W4286492109 cites W3041776387 @default.
- W4286492109 cites W3043533097 @default.
- W4286492109 cites W3095979953 @default.
- W4286492109 cites W3102391325 @default.
- W4286492109 cites W3112051302 @default.
- W4286492109 cites W3136523593 @default.
- W4286492109 cites W3182238355 @default.
- W4286492109 cites W4229650096 @default.
- W4286492109 cites W4247869890 @default.
- W4286492109 doi "https://doi.org/10.1137/21m1395302" @default.
- W4286492109 hasPublicationYear "2022" @default.
- W4286492109 type Work @default.
- W4286492109 citedByCount "0" @default.
- W4286492109 crossrefType "journal-article" @default.
- W4286492109 hasAuthorship W4286492109A5047540105 @default.
- W4286492109 hasAuthorship W4286492109A5076054793 @default.
- W4286492109 hasConcept C111472728 @default.
- W4286492109 hasConcept C112680207 @default.
- W4286492109 hasConcept C12108790 @default.
- W4286492109 hasConcept C126255220 @default.
- W4286492109 hasConcept C137836250 @default.
- W4286492109 hasConcept C138885662 @default.
- W4286492109 hasConcept C14036430 @default.
- W4286492109 hasConcept C145446738 @default.
- W4286492109 hasConcept C157972887 @default.
- W4286492109 hasConcept C162324750 @default.
- W4286492109 hasConcept C17744445 @default.
- W4286492109 hasConcept C191795146 @default.
- W4286492109 hasConcept C199539241 @default.
- W4286492109 hasConcept C2524010 @default.
- W4286492109 hasConcept C2777303404 @default.
- W4286492109 hasConcept C2780586882 @default.
- W4286492109 hasConcept C33923547 @default.
- W4286492109 hasConcept C50522688 @default.
- W4286492109 hasConcept C78458016 @default.
- W4286492109 hasConcept C79187972 @default.
- W4286492109 hasConcept C86803240 @default.
- W4286492109 hasConceptScore W4286492109C111472728 @default.
- W4286492109 hasConceptScore W4286492109C112680207 @default.
- W4286492109 hasConceptScore W4286492109C12108790 @default.
- W4286492109 hasConceptScore W4286492109C126255220 @default.
- W4286492109 hasConceptScore W4286492109C137836250 @default.
- W4286492109 hasConceptScore W4286492109C138885662 @default.
- W4286492109 hasConceptScore W4286492109C14036430 @default.
- W4286492109 hasConceptScore W4286492109C145446738 @default.
- W4286492109 hasConceptScore W4286492109C157972887 @default.
- W4286492109 hasConceptScore W4286492109C162324750 @default.
- W4286492109 hasConceptScore W4286492109C17744445 @default.
- W4286492109 hasConceptScore W4286492109C191795146 @default.
- W4286492109 hasConceptScore W4286492109C199539241 @default.
- W4286492109 hasConceptScore W4286492109C2524010 @default.
- W4286492109 hasConceptScore W4286492109C2777303404 @default.
- W4286492109 hasConceptScore W4286492109C2780586882 @default.
- W4286492109 hasConceptScore W4286492109C33923547 @default.
- W4286492109 hasConceptScore W4286492109C50522688 @default.
- W4286492109 hasConceptScore W4286492109C78458016 @default.
- W4286492109 hasConceptScore W4286492109C79187972 @default.
- W4286492109 hasConceptScore W4286492109C86803240 @default.
- W4286492109 hasFunder F4320306076 @default.