FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2765432750> ?p ?o ?g. }

• W2765432750 abstract "Motivated by applications arising from large scale optimization and machine learning, we consider stochastic quasi-Newton (SQN) methods for solving unconstrained convex optimization problems. The convergence analysis of the SQN methods, both full and limited-memory variants, require the objective function to be strongly convex. However, this assumption is fairly restrictive and does not hold for applications such as minimizing the logistic regression loss function. To the best of our knowledge, no rate statements currently exist for SQN methods in the absence of such an assumption. Also, among the existing first-order methods for addressing stochastic optimization problems with merely convex objectives, those equipped with provable convergence rates employ averaging. However, this averaging technique has a detrimental impact on inducing sparsity. Motivated by these gaps, the main contributions of the paper are as follows: (i) Addressing large scale stochastic optimization problems, we develop an iteratively regularized stochastic limited-memory BFGS (IRS-LBFGS) algorithm, where the stepsize, regularization parameter, and the Hessian inverse approximation matrix are updated iteratively. We establish the convergence to an optimal solution of the original problem both in an almost-sure and mean senses. We derive the convergence rate in terms of the objective function's values and show that it is of the order $mathcal{O}left(k^{-left(frac{1}{3}-epsilonright)}right)$, where $epsilon$ is an arbitrary small positive scalar; (ii) In deterministic regime, we show that the regularized limited-memory BFGS algorithm displays a rate of the order $mathcal{O}left(frac{1}{k^{1 -epsilon'}}right)$, where $epsilon'$ is an arbitrary small positive scalar. We present our numerical experiments performed on a large scale text classification problem." @default.
• W2765432750 created "2017-11-10" @default.
• W2765432750 creator A5003164670 @default.
• W2765432750 creator A5047034022 @default.
• W2765432750 creator A5052663817 @default.
• W2765432750 date "2017-10-16" @default.
• W2765432750 modified "2023-09-28" @default.
• W2765432750 title "On stochastic and deterministic quasi-Newton methods for non-Strongly convex optimization: Asymptotic convergence and rate analysis." @default.
• W2765432750 cites W114517082 @default.
• W2765432750 cites W1491622225 @default.
• W2765432750 cites W1568288633 @default.
• W2765432750 cites W1592294486 @default.
• W2765432750 cites W1822292100 @default.
• W2765432750 cites W1925698896 @default.
• W2765432750 cites W1992208280 @default.
• W2765432750 cites W1994616650 @default.
• W2765432750 cites W1998880679 @default.
• W2765432750 cites W2008796819 @default.
• W2765432750 cites W2038210983 @default.
• W2765432750 cites W2042173174 @default.
• W2765432750 cites W2043819123 @default.
• W2765432750 cites W2051434435 @default.
• W2765432750 cites W2072265605 @default.
• W2765432750 cites W2078409719 @default.
• W2765432750 cites W2080335539 @default.
• W2765432750 cites W2092554297 @default.
• W2765432750 cites W2095133175 @default.
• W2765432750 cites W2131448432 @default.
• W2765432750 cites W2137515395 @default.
• W2765432750 cites W2150102617 @default.
• W2765432750 cites W2570633406 @default.
• W2765432750 cites W2587483164 @default.
• W2765432750 cites W2952215077 @default.
• W2765432750 cites W2963156201 @default.
• W2765432750 cites W2963575360 @default.
• W2765432750 cites W2963941964 @default.
• W2765432750 cites W2964303576 @default.
• W2765432750 cites W3029645440 @default.
• W2765432750 cites W3104398353 @default.
• W2765432750 cites W3106438735 @default.
• W2765432750 hasPublicationYear "2017" @default.
• W2765432750 type Work @default.
• W2765432750 sameAs 2765432750 @default.
• W2765432750 citedByCount "2" @default.
• W2765432750 countsByYear W27654327502020 @default.
• W2765432750 crossrefType "posted-content" @default.
• W2765432750 hasAuthorship W2765432750A5003164670 @default.
• W2765432750 hasAuthorship W2765432750A5047034022 @default.
• W2765432750 hasAuthorship W2765432750A5052663817 @default.
• W2765432750 hasConcept C106159729 @default.
• W2765432750 hasConcept C112680207 @default.
• W2765432750 hasConcept C126255220 @default.
• W2765432750 hasConcept C127162648 @default.
• W2765432750 hasConcept C132721684 @default.
• W2765432750 hasConcept C137836250 @default.
• W2765432750 hasConcept C14036430 @default.
• W2765432750 hasConcept C145446738 @default.
• W2765432750 hasConcept C151319957 @default.
• W2765432750 hasConcept C162324750 @default.
• W2765432750 hasConcept C194387892 @default.
• W2765432750 hasConcept C203616005 @default.
• W2765432750 hasConcept C2524010 @default.
• W2765432750 hasConcept C2777303404 @default.
• W2765432750 hasConcept C28826006 @default.
• W2765432750 hasConcept C31258907 @default.
• W2765432750 hasConcept C33923547 @default.
• W2765432750 hasConcept C41008148 @default.
• W2765432750 hasConcept C50522688 @default.
• W2765432750 hasConcept C57869625 @default.
• W2765432750 hasConcept C72134830 @default.
• W2765432750 hasConcept C78458016 @default.
• W2765432750 hasConcept C86803240 @default.
• W2765432750 hasConceptScore W2765432750C106159729 @default.
• W2765432750 hasConceptScore W2765432750C112680207 @default.
• W2765432750 hasConceptScore W2765432750C126255220 @default.
• W2765432750 hasConceptScore W2765432750C127162648 @default.
• W2765432750 hasConceptScore W2765432750C132721684 @default.
• W2765432750 hasConceptScore W2765432750C137836250 @default.
• W2765432750 hasConceptScore W2765432750C14036430 @default.
• W2765432750 hasConceptScore W2765432750C145446738 @default.
• W2765432750 hasConceptScore W2765432750C151319957 @default.
• W2765432750 hasConceptScore W2765432750C162324750 @default.
• W2765432750 hasConceptScore W2765432750C194387892 @default.
• W2765432750 hasConceptScore W2765432750C203616005 @default.
• W2765432750 hasConceptScore W2765432750C2524010 @default.
• W2765432750 hasConceptScore W2765432750C2777303404 @default.
• W2765432750 hasConceptScore W2765432750C28826006 @default.
• W2765432750 hasConceptScore W2765432750C31258907 @default.
• W2765432750 hasConceptScore W2765432750C33923547 @default.
• W2765432750 hasConceptScore W2765432750C41008148 @default.
• W2765432750 hasConceptScore W2765432750C50522688 @default.
• W2765432750 hasConceptScore W2765432750C57869625 @default.
• W2765432750 hasConceptScore W2765432750C72134830 @default.
• W2765432750 hasConceptScore W2765432750C78458016 @default.
• W2765432750 hasConceptScore W2765432750C86803240 @default.
• W2765432750 hasOpenAccess W2765432750 @default.
• W2765432750 hasRelatedWork W1592294486 @default.
• W2765432750 hasRelatedWork W2049556680 @default.
• W2765432750 hasRelatedWork W2297836514 @default.
• W2765432750 hasRelatedWork W2398337421 @default.

• next