Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891447341> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2891447341 endingPage "1919" @default.
- W2891447341 startingPage "1910" @default.
- W2891447341 abstract "Stochastic convex optimization algorithms are the most popular way to train machine learning models on large-scale data. Scaling up the training process of these models is crucial, but the most popular algorithm, Stochastic Gradient Descent (SGD), is a serial method that is surprisingly hard to parallelize. In this paper, we propose an efficient distributed stochastic optimization method by combining adaptivity with variance reduction techniques. Our analysis yields a linear speedup in the number of machines, constant memory footprint, and only a logarithmic number of communication rounds. Critically, our approach is a black-box reduction that parallelizes any serial online learning algorithm, streamlining prior analysis and allowing us to leverage the significant progress that has been made in designing adaptive algorithms. In particular, we achieve optimal convergence rates without any prior knowledge of smoothness parameters, yielding a more robust algorithm that reduces the need for hyperparameter tuning. We implement our algorithm in the Spark distributed framework and exhibit dramatic performance gains on large-scale logistic regression problems." @default.
- W2891447341 created "2018-09-27" @default.
- W2891447341 creator A5047520070 @default.
- W2891447341 creator A5066011484 @default.
- W2891447341 date "2018-02-01" @default.
- W2891447341 modified "2023-10-04" @default.
- W2891447341 title "Distributed Stochastic Optimization via Adaptive SGD" @default.
- W2891447341 hasPublicationYear "2018" @default.
- W2891447341 type Work @default.
- W2891447341 sameAs 2891447341 @default.
- W2891447341 citedByCount "9" @default.
- W2891447341 countsByYear W28914473412019 @default.
- W2891447341 countsByYear W28914473412021 @default.
- W2891447341 crossrefType "proceedings-article" @default.
- W2891447341 hasAuthorship W2891447341A5047520070 @default.
- W2891447341 hasAuthorship W2891447341A5066011484 @default.
- W2891447341 hasConcept C111919701 @default.
- W2891447341 hasConcept C11413529 @default.
- W2891447341 hasConcept C119857082 @default.
- W2891447341 hasConcept C121955636 @default.
- W2891447341 hasConcept C126255220 @default.
- W2891447341 hasConcept C134306372 @default.
- W2891447341 hasConcept C144133560 @default.
- W2891447341 hasConcept C153083717 @default.
- W2891447341 hasConcept C173608175 @default.
- W2891447341 hasConcept C194387892 @default.
- W2891447341 hasConcept C196083921 @default.
- W2891447341 hasConcept C206688291 @default.
- W2891447341 hasConcept C33923547 @default.
- W2891447341 hasConcept C39927690 @default.
- W2891447341 hasConcept C41008148 @default.
- W2891447341 hasConcept C50644808 @default.
- W2891447341 hasConcept C62644790 @default.
- W2891447341 hasConcept C68339613 @default.
- W2891447341 hasConcept C74912251 @default.
- W2891447341 hasConcept C8642999 @default.
- W2891447341 hasConceptScore W2891447341C111919701 @default.
- W2891447341 hasConceptScore W2891447341C11413529 @default.
- W2891447341 hasConceptScore W2891447341C119857082 @default.
- W2891447341 hasConceptScore W2891447341C121955636 @default.
- W2891447341 hasConceptScore W2891447341C126255220 @default.
- W2891447341 hasConceptScore W2891447341C134306372 @default.
- W2891447341 hasConceptScore W2891447341C144133560 @default.
- W2891447341 hasConceptScore W2891447341C153083717 @default.
- W2891447341 hasConceptScore W2891447341C173608175 @default.
- W2891447341 hasConceptScore W2891447341C194387892 @default.
- W2891447341 hasConceptScore W2891447341C196083921 @default.
- W2891447341 hasConceptScore W2891447341C206688291 @default.
- W2891447341 hasConceptScore W2891447341C33923547 @default.
- W2891447341 hasConceptScore W2891447341C39927690 @default.
- W2891447341 hasConceptScore W2891447341C41008148 @default.
- W2891447341 hasConceptScore W2891447341C50644808 @default.
- W2891447341 hasConceptScore W2891447341C62644790 @default.
- W2891447341 hasConceptScore W2891447341C68339613 @default.
- W2891447341 hasConceptScore W2891447341C74912251 @default.
- W2891447341 hasConceptScore W2891447341C8642999 @default.
- W2891447341 hasLocation W28914473411 @default.
- W2891447341 hasOpenAccess W2891447341 @default.
- W2891447341 hasPrimaryLocation W28914473411 @default.
- W2891447341 hasRelatedWork W1501362825 @default.
- W2891447341 hasRelatedWork W1570678512 @default.
- W2891447341 hasRelatedWork W2130062883 @default.
- W2891447341 hasRelatedWork W2138243089 @default.
- W2891447341 hasRelatedWork W2291259925 @default.
- W2891447341 hasRelatedWork W2347281465 @default.
- W2891447341 hasRelatedWork W2484096406 @default.
- W2891447341 hasRelatedWork W2751713192 @default.
- W2891447341 hasRelatedWork W2786546591 @default.
- W2891447341 hasRelatedWork W2919417563 @default.
- W2891447341 hasRelatedWork W2937268935 @default.
- W2891447341 hasRelatedWork W2949996120 @default.
- W2891447341 hasRelatedWork W2962767613 @default.
- W2891447341 hasRelatedWork W2962961534 @default.
- W2891447341 hasRelatedWork W2964304412 @default.
- W2891447341 hasRelatedWork W2981831462 @default.
- W2891447341 hasRelatedWork W3012524561 @default.
- W2891447341 hasRelatedWork W3015640161 @default.
- W2891447341 hasRelatedWork W3042762796 @default.
- W2891447341 hasRelatedWork W3199109861 @default.
- W2891447341 hasVolume "31" @default.
- W2891447341 isParatext "false" @default.
- W2891447341 isRetracted "false" @default.
- W2891447341 magId "2891447341" @default.
- W2891447341 workType "article" @default.