litlas
ログインアカウント作成

Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization

著者: Martin Jaggi - International Conference on Machine Learning, ICML 2013 被引用: 1,518

The authors compare recovery and the post-anaesthetic period in 45 patients anaesthetised with a combination of either pentothal, nitrous oxide, fluothane and dolosal (group 1, 24 subjects), or of pentothal, nitrous oxide and phenoperidine (group 2, 21 subjects). The quality of recovery was judged at the end of anaesthesia by determining of occurrence of the first response to 3 types of stimulation (calling the name, noise and pain) and the density of these responses during each minute. During the post-anaesthetic period the respective percentages of wakefulness and sleep were calculated. In this way the authors demonstrate a significant (P less than 0.01) shortening in recovery time for group 2, reactivity to own name occurring first in both groups, and a very significant (P less than 0.001) increase in the percentage of physiological sleep in subjects of group 2 during the post-anaesthetic stage.

An algorithm forquadratic programmingAn algorithm for quadratic programmingConstrained minimizationmethodsConstrained minimization methodsConditional gradientalgorithms with open…Conditional gradient algorithms with open loop step size rulesSome comments on Wolfe's'away step'Some comments on Wolfe's 'away step'Coresets, sparse greedyapproximation, and the…Coresets, sparse greedy approximation, and the Frank-Wolfe algorithmSparse ApproximateSolutions to…Sparse Approximate Solutions to Semidefinite ProgramsA Simple Algorithm forNuclear Norm Regularize…A Simple Algorithm for Nuclear Norm Regularized ProblemsSparse ConvexOptimization Methods fo…Sparse Convex Optimization Methods for Machine LearningProjection-free OnlineLearningProjection-free Online LearningAccelerated Training forMatrix-norm…Accelerated Training for Matrix-norm Regularization: A Boosting ApproachLifted coordinatedescent for learning…Lifted coordinate descent for learning with trace-norm regularizationGreedy Approximation inConvex OptimizationGreedy Approximation in Convex OptimizationLearning with SubmodularFunctions: A Convex…Learning with Submodular Functions: A Convex Optimization PerspectiveConvex Optimization forBig Data: Scalable…Convex Optimization for Big Data: Scalable, randomized, and parallel algorithms for big data analyticsFaster Rates for theFrank-Wolfe Method over…Faster Rates for the Frank-Wolfe Method over Strongly-Convex SetsScalable Robust MatrixRecovery: Frank-Wolfe…Scalable Robust Matrix Recovery: Frank-Wolfe Meets Proximal MethodsParallel and DistributedBlock-Coordinate…Parallel and Distributed Block-Coordinate Frank-Wolfe AlgorithmsAn Overview of Low-RankMatrix Recovery From…An Overview of Low-Rank Matrix Recovery From Incomplete ObservationsDecomposition-InvariantConditional Gradient fo…Decomposition-Invariant Conditional Gradient for General Polytopes with Line SearchConvex FactorizationMachine for…Convex Factorization Machine for Toxicogenomics PredictionGeneralizedself-concordant…Generalized self-concordant functions: a recipe for Newton-type methodsSafe Screening for theGeneralized Conditional…Safe Screening for the Generalized Conditional Gradient MethodHow Does Momentum HelpFrank Wolfe?How Does Momentum Help Frank Wolfe?Locally AcceleratedConditional GradientsLocally Accelerated Conditional GradientsRevisiting Frank-Wolfe:Projection-Free Sparse…Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization過去の参考文献中心の論文この論文を引用する論文古い新しい

ノードをクリックするとフォーカスを固定、空白をクリックすると本論文に戻ります。ホバーで一時的にプレビューできます。各ノードのページはタイトルから開けます。