FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1915957564> ?p ?o ?g. }

• W1915957564 abstract "We consider the problem of minimizing a sum of $n$ functions over a convex parameter set $mathcal{C} subset mathbb{R}^p$ where $ngg pgg 1$. In this regime, algorithms which utilize sub-sampling techniques are known to be effective. In this paper, we use sub-sampling techniques together with low-rank approximation to design a new randomized batch algorithm which possesses comparable convergence rate to Newton's method, yet has much smaller per-iteration cost. The proposed algorithm is robust in terms of starting point and step size, and enjoys a composite convergence rate, namely, quadratic convergence at start and linear convergence when the iterate is close to the minimizer. We develop its theoretical analysis which also allows us to select near-optimal algorithm parameters. Our theoretical results can be used to obtain convergence rates of previously proposed sub-sampling based algorithms as well. We demonstrate how our results apply to well-known machine learning problems. Lastly, we evaluate the performance of our algorithm on several datasets under various scenarios." @default.
• W1915957564 created "2016-06-24" @default.
• W1915957564 creator A5011999109 @default.
• W1915957564 creator A5022491830 @default.
• W1915957564 date "2015-08-12" @default.
• W1915957564 modified "2023-09-27" @default.
• W1915957564 title "Convergence rates of sub-sampled Newton methods" @default.
• W1915957564 cites W114517082 @default.
• W1915957564 cites W144691381 @default.
• W1915957564 cites W1491622225 @default.
• W1915957564 cites W1554663460 @default.
• W1915957564 cites W1556219185 @default.
• W1915957564 cites W1560724230 @default.
• W1915957564 cites W1598497354 @default.
• W1915957564 cites W1707676469 @default.
• W1915957564 cites W1959255040 @default.
• W1915957564 cites W196761320 @default.
• W1915957564 cites W1991083751 @default.
• W1915957564 cites W2000200144 @default.
• W1915957564 cites W2005136695 @default.
• W1915957564 cites W2038210983 @default.
• W1915957564 cites W2056641273 @default.
• W1915957564 cites W2062294426 @default.
• W1915957564 cites W2078394884 @default.
• W1915957564 cites W2078409719 @default.
• W1915957564 cites W2094644779 @default.
• W1915957564 cites W2103972604 @default.
• W1915957564 cites W2121116595 @default.
• W1915957564 cites W2131172946 @default.
• W1915957564 cites W2146502635 @default.
• W1915957564 cites W2147898188 @default.
• W1915957564 cites W2148603752 @default.
• W1915957564 cites W2158044763 @default.
• W1915957564 cites W2170582628 @default.
• W1915957564 cites W2242968763 @default.
• W1915957564 cites W2287714000 @default.
• W1915957564 cites W2296319761 @default.
• W1915957564 cites W2951301236 @default.
• W1915957564 cites W2953242304 @default.
• W1915957564 cites W2963156201 @default.
• W1915957564 cites W2969945254 @default.
• W1915957564 cites W3103657382 @default.
• W1915957564 cites W3120740533 @default.
• W1915957564 cites W3141595720 @default.
• W1915957564 cites W592715486 @default.
• W1915957564 hasPublicationYear "2015" @default.
• W1915957564 type Work @default.
• W1915957564 sameAs 1915957564 @default.
• W1915957564 citedByCount "36" @default.
• W1915957564 countsByYear W19159575642015 @default.
• W1915957564 countsByYear W19159575642016 @default.
• W1915957564 countsByYear W19159575642017 @default.
• W1915957564 countsByYear W19159575642018 @default.
• W1915957564 countsByYear W19159575642019 @default.
• W1915957564 countsByYear W19159575642020 @default.
• W1915957564 countsByYear W19159575642021 @default.
• W1915957564 crossrefType "posted-content" @default.
• W1915957564 hasAuthorship W1915957564A5011999109 @default.
• W1915957564 hasAuthorship W1915957564A5022491830 @default.
• W1915957564 hasConcept C106131492 @default.
• W1915957564 hasConcept C112680207 @default.
• W1915957564 hasConcept C11413529 @default.
• W1915957564 hasConcept C114614502 @default.
• W1915957564 hasConcept C126255220 @default.
• W1915957564 hasConcept C127162648 @default.
• W1915957564 hasConcept C129844170 @default.
• W1915957564 hasConcept C140779682 @default.
• W1915957564 hasConcept C145446738 @default.
• W1915957564 hasConcept C162324750 @default.
• W1915957564 hasConcept C164226766 @default.
• W1915957564 hasConcept C177264268 @default.
• W1915957564 hasConcept C199360897 @default.
• W1915957564 hasConcept C2524010 @default.
• W1915957564 hasConcept C2777303404 @default.
• W1915957564 hasConcept C28826006 @default.
• W1915957564 hasConcept C31258907 @default.
• W1915957564 hasConcept C31972630 @default.
• W1915957564 hasConcept C33923547 @default.
• W1915957564 hasConcept C41008148 @default.
• W1915957564 hasConcept C50522688 @default.
• W1915957564 hasConcept C57869625 @default.
• W1915957564 hasConceptScore W1915957564C106131492 @default.
• W1915957564 hasConceptScore W1915957564C112680207 @default.
• W1915957564 hasConceptScore W1915957564C11413529 @default.
• W1915957564 hasConceptScore W1915957564C114614502 @default.
• W1915957564 hasConceptScore W1915957564C126255220 @default.
• W1915957564 hasConceptScore W1915957564C127162648 @default.
• W1915957564 hasConceptScore W1915957564C129844170 @default.
• W1915957564 hasConceptScore W1915957564C140779682 @default.
• W1915957564 hasConceptScore W1915957564C145446738 @default.
• W1915957564 hasConceptScore W1915957564C162324750 @default.
• W1915957564 hasConceptScore W1915957564C164226766 @default.
• W1915957564 hasConceptScore W1915957564C177264268 @default.
• W1915957564 hasConceptScore W1915957564C199360897 @default.
• W1915957564 hasConceptScore W1915957564C2524010 @default.
• W1915957564 hasConceptScore W1915957564C2777303404 @default.
• W1915957564 hasConceptScore W1915957564C28826006 @default.
• W1915957564 hasConceptScore W1915957564C31258907 @default.
• W1915957564 hasConceptScore W1915957564C31972630 @default.
• W1915957564 hasConceptScore W1915957564C33923547 @default.

• next