Matches in SemOpenAlex for { <https://semopenalex.org/work/W3018617837> ?p ?o ?g. }
- W3018617837 abstract "Classical extragradient schemes and their stochastic counterpart represent a cornerstone for resolving monotone variational inequality problems. Yet, such schemes have a per-iteration complexity of two projections onto a convex set and require two evaluations of the map, the former of which could be relatively expensive if $X$ is a complicated set. We consider two related avenues where the per-iteration complexity is significantly reduced: (i) A stochastic projected reflected gradient method requiring a single evaluation of the map and a single projection; and (ii) A stochastic subgradient extragradient method that requires two evaluations of the map, a single projection onto $X$, and a significantly cheaper projection (onto a halfspace) computable in closed form. Under a variance-reduced framework reliant on a sample-average of the map based on an increasing batch-size, we prove almost sure (a.s.) convergence of the iterates to a random point in the solution set for both schemes. Additionally, both schemes display a non-asymptotic rate of $mathcal{O}(1/K)$ where $K$ denotes the number of iterations; notably, both rates match those obtained in deterministic regimes. To address feasibility sets given by the intersection of a large number of convex constraints, we adapt both of the aforementioned schemes to a random projection framework. We then show that the random projection analogs of both schemes also display a.s. convergence under a weak-sharpness requirement; furthermore, without imposing the weak-sharpness requirement, both schemes are characterized by a provable rate of $mathcal{O}(1/sqrt{K})$ in terms of the gap function of the projection of the averaged sequence onto $X$ as well as the infeasibility of this sequence. Preliminary numerics support theoretical findings and the schemes outperform standard extragradient schemes in terms of the per-iteration complexity." @default.
- W3018617837 created "2020-05-01" @default.
- W3018617837 creator A5047034022 @default.
- W3018617837 creator A5066114861 @default.
- W3018617837 date "2019-04-24" @default.
- W3018617837 modified "2023-09-25" @default.
- W3018617837 title "On the analysis of variance-reduced and randomized projection variants of single projection schemes for monotone stochastic variational inequality problems" @default.
- W3018617837 cites W12587253 @default.
- W3018617837 cites W1519983590 @default.
- W3018617837 cites W1541527977 @default.
- W3018617837 cites W1543439990 @default.
- W3018617837 cites W1568288633 @default.
- W3018617837 cites W1569990960 @default.
- W3018617837 cites W1976597683 @default.
- W3018617837 cites W1991765628 @default.
- W3018617837 cites W1992208280 @default.
- W3018617837 cites W1994616650 @default.
- W3018617837 cites W1997949764 @default.
- W3018617837 cites W2008796819 @default.
- W3018617837 cites W2010659474 @default.
- W3018617837 cites W2012180727 @default.
- W3018617837 cites W2026355589 @default.
- W3018617837 cites W2039696315 @default.
- W3018617837 cites W2055828890 @default.
- W3018617837 cites W205960364 @default.
- W3018617837 cites W2061627126 @default.
- W3018617837 cites W2073750241 @default.
- W3018617837 cites W2089559088 @default.
- W3018617837 cites W2096624719 @default.
- W3018617837 cites W2107438106 @default.
- W3018617837 cites W2110412969 @default.
- W3018617837 cites W2112383528 @default.
- W3018617837 cites W2124181538 @default.
- W3018617837 cites W2135482703 @default.
- W3018617837 cites W2158898097 @default.
- W3018617837 cites W2197814125 @default.
- W3018617837 cites W2295489065 @default.
- W3018617837 cites W2460240966 @default.
- W3018617837 cites W2568744357 @default.
- W3018617837 cites W2593248927 @default.
- W3018617837 cites W2963155955 @default.
- W3018617837 cites W2963861305 @default.
- W3018617837 cites W2964121860 @default.
- W3018617837 cites W2971302301 @default.
- W3018617837 cites W3007067459 @default.
- W3018617837 cites W3037593317 @default.
- W3018617837 cites W3100033291 @default.
- W3018617837 cites W3101497372 @default.
- W3018617837 doi "https://doi.org/10.48550/arxiv.1904.11076" @default.
- W3018617837 hasPublicationYear "2019" @default.
- W3018617837 type Work @default.
- W3018617837 sameAs 3018617837 @default.
- W3018617837 citedByCount "0" @default.
- W3018617837 crossrefType "posted-content" @default.
- W3018617837 hasAuthorship W3018617837A5047034022 @default.
- W3018617837 hasAuthorship W3018617837A5066114861 @default.
- W3018617837 hasBestOaLocation W30186178371 @default.
- W3018617837 hasConcept C112680207 @default.
- W3018617837 hasConcept C11413529 @default.
- W3018617837 hasConcept C118615104 @default.
- W3018617837 hasConcept C126255220 @default.
- W3018617837 hasConcept C127162648 @default.
- W3018617837 hasConcept C127413603 @default.
- W3018617837 hasConcept C134306372 @default.
- W3018617837 hasConcept C140479938 @default.
- W3018617837 hasConcept C146978453 @default.
- W3018617837 hasConcept C157972887 @default.
- W3018617837 hasConcept C158968445 @default.
- W3018617837 hasConcept C161999928 @default.
- W3018617837 hasConcept C162324750 @default.
- W3018617837 hasConcept C2524010 @default.
- W3018617837 hasConcept C2777303404 @default.
- W3018617837 hasConcept C2834757 @default.
- W3018617837 hasConcept C28826006 @default.
- W3018617837 hasConcept C31258907 @default.
- W3018617837 hasConcept C33923547 @default.
- W3018617837 hasConcept C41008148 @default.
- W3018617837 hasConcept C49870271 @default.
- W3018617837 hasConcept C50522688 @default.
- W3018617837 hasConcept C57493831 @default.
- W3018617837 hasConcept C57869625 @default.
- W3018617837 hasConcept C64543145 @default.
- W3018617837 hasConceptScore W3018617837C112680207 @default.
- W3018617837 hasConceptScore W3018617837C11413529 @default.
- W3018617837 hasConceptScore W3018617837C118615104 @default.
- W3018617837 hasConceptScore W3018617837C126255220 @default.
- W3018617837 hasConceptScore W3018617837C127162648 @default.
- W3018617837 hasConceptScore W3018617837C127413603 @default.
- W3018617837 hasConceptScore W3018617837C134306372 @default.
- W3018617837 hasConceptScore W3018617837C140479938 @default.
- W3018617837 hasConceptScore W3018617837C146978453 @default.
- W3018617837 hasConceptScore W3018617837C157972887 @default.
- W3018617837 hasConceptScore W3018617837C158968445 @default.
- W3018617837 hasConceptScore W3018617837C161999928 @default.
- W3018617837 hasConceptScore W3018617837C162324750 @default.
- W3018617837 hasConceptScore W3018617837C2524010 @default.
- W3018617837 hasConceptScore W3018617837C2777303404 @default.
- W3018617837 hasConceptScore W3018617837C2834757 @default.
- W3018617837 hasConceptScore W3018617837C28826006 @default.
- W3018617837 hasConceptScore W3018617837C31258907 @default.