FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2947996939> ?p ?o ?g. }

• W2947996939 abstract "We consider nonconvex-concave minimax problems, $min_{mathbf{x}} max_{mathbf{y} in mathcal{Y}} f(mathbf{x}, mathbf{y})$, where $f$ is nonconvex in $mathbf{x}$ but concave in $mathbf{y}$ and $mathcal{Y}$ is a convex and bounded set. One of the most popular algorithms for solving this problem is the celebrated gradient descent ascent (GDA) algorithm, which has been widely used in machine learning, control theory and economics. Despite the extensive convergence results for the convex-concave setting, GDA with equal stepsize can converge to limit cycles or even diverge in a general setting. In this paper, we present the complexity results on two-time-scale GDA for solving nonconvex-concave minimax problems, showing that the algorithm can find a stationary point of the function $Phi(cdot) := max_{mathbf{y} in mathcal{Y}} f(cdot, mathbf{y})$ efficiently. To the best our knowledge, this is the first nonasymptotic analysis for two-time-scale GDA in this setting, shedding light on its superior practical performance in training generative adversarial networks (GANs) and other real applications." @default.
• W2947996939 created "2019-06-07" @default.
• W2947996939 creator A5049812527 @default.
• W2947996939 creator A5082311500 @default.
• W2947996939 creator A5083720030 @default.
• W2947996939 date "2019-06-01" @default.
• W2947996939 modified "2023-09-26" @default.
• W2947996939 title "On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems" @default.
• W2947996939 cites W1519983590 @default.
• W2947996939 cites W1570963478 @default.
• W2947996939 cites W1578630563 @default.
• W2947996939 cites W1985077192 @default.
• W2947996939 cites W1993203591 @default.
• W2947996939 cites W2020123437 @default.
• W2947996939 cites W2075567596 @default.
• W2947996939 cites W2080844831 @default.
• W2947996939 cites W2089559088 @default.
• W2947996939 cites W2099471712 @default.
• W2947996939 cites W2116200501 @default.
• W2947996939 cites W2149254401 @default.
• W2947996939 cites W2151565294 @default.
• W2947996939 cites W2169225433 @default.
• W2947996939 cites W2324833515 @default.
• W2947996939 cites W2475559389 @default.
• W2947996939 cites W2564590721 @default.
• W2947996939 cites W2788053000 @default.
• W2947996939 cites W2788819334 @default.
• W2947996939 cites W2803117117 @default.
• W2947996939 cites W2811481615 @default.
• W2947996939 cites W2894677249 @default.
• W2947996939 cites W2895628298 @default.
• W2947996939 cites W2900976719 @default.
• W2947996939 cites W2907669392 @default.
• W2947996939 cites W2911319680 @default.
• W2947996939 cites W2948517632 @default.
• W2947996939 cites W2950041755 @default.
• W2947996939 cites W2951567597 @default.
• W2947996939 cites W2952392021 @default.
• W2947996939 cites W2962717811 @default.
• W2947996939 cites W2962723467 @default.
• W2947996939 cites W2962723573 @default.
• W2947996939 cites W2962979365 @default.
• W2947996939 cites W2963147599 @default.
• W2947996939 cites W2963190258 @default.
• W2947996939 cites W2963207607 @default.
• W2947996939 cites W2963353224 @default.
• W2947996939 cites W2963539647 @default.
• W2947996939 cites W2963647223 @default.
• W2947996939 cites W2963809785 @default.
• W2947996939 cites W2963981733 @default.
• W2947996939 cites W2964067523 @default.
• W2947996939 cites W2964070557 @default.
• W2947996939 cites W2964121860 @default.
• W2947996939 cites W2964253222 @default.
• W2947996939 cites W2964334726 @default.
• W2947996939 cites W2970416783 @default.
• W2947996939 cites W2970552792 @default.
• W2947996939 cites W3016604587 @default.
• W2947996939 cites W3037593317 @default.
• W2947996939 cites W3141595720 @default.
• W2947996939 cites W646347605 @default.
• W2947996939 doi "https://doi.org/10.48550/arxiv.1906.00331" @default.
• W2947996939 hasPublicationYear "2019" @default.
• W2947996939 type Work @default.
• W2947996939 sameAs 2947996939 @default.
• W2947996939 citedByCount "44" @default.
• W2947996939 countsByYear W29479969392019 @default.
• W2947996939 countsByYear W29479969392020 @default.
• W2947996939 countsByYear W29479969392021 @default.
• W2947996939 countsByYear W29479969392022 @default.
• W2947996939 crossrefType "posted-content" @default.
• W2947996939 hasAuthorship W2947996939A5049812527 @default.
• W2947996939 hasAuthorship W2947996939A5082311500 @default.
• W2947996939 hasAuthorship W2947996939A5083720030 @default.
• W2947996939 hasBestOaLocation W29479969391 @default.
• W2947996939 hasConcept C112680207 @default.
• W2947996939 hasConcept C114614502 @default.
• W2947996939 hasConcept C126255220 @default.
• W2947996939 hasConcept C134306372 @default.
• W2947996939 hasConcept C14036430 @default.
• W2947996939 hasConcept C145446738 @default.
• W2947996939 hasConcept C149728462 @default.
• W2947996939 hasConcept C151201525 @default.
• W2947996939 hasConcept C153258448 @default.
• W2947996939 hasConcept C154945302 @default.
• W2947996939 hasConcept C162324750 @default.
• W2947996939 hasConcept C189237950 @default.
• W2947996939 hasConcept C2524010 @default.
• W2947996939 hasConcept C2777303404 @default.
• W2947996939 hasConcept C2780861221 @default.
• W2947996939 hasConcept C33923547 @default.
• W2947996939 hasConcept C34388435 @default.
• W2947996939 hasConcept C41008148 @default.
• W2947996939 hasConcept C50522688 @default.
• W2947996939 hasConcept C50644808 @default.
• W2947996939 hasConcept C66690126 @default.
• W2947996939 hasConcept C78458016 @default.
• W2947996939 hasConcept C86803240 @default.
• W2947996939 hasConceptScore W2947996939C112680207 @default.
• W2947996939 hasConceptScore W2947996939C114614502 @default.

• next