BoostingforOnlineConvexOptimizationEladHazan12KaranSingh3Abstractetal.,2012).ItiswellestablishedthattheregretcanbeboundedbyO(TlogH),whereHisthenumberofWeconsiderthedecision-makingframeworkofexperts...
BilevelOptimization:ConvergenceAnalysisandEnhancedDesignKaiyiJi1JunjieYang1YingbinLiang1AbstractOptimization(Franceschietal.,2018;Shabanetal.,2019;Feurer&Hutter,2019),reinforcementlearning(Konda&Bi...
Bias-RobustBayesianOptimizationviaDuelingBanditsJohannesKirschner1AndreasKrause1AbstractWestudyasettingwherethelearner’sobjectiveistomax-imizeanunknownfunctionf:X→RwithadditiveWeconsiderBayesiano...
ADOM:AcceleratedDecentralizedOptimizationMethodforTime-VaryingNetworksDmitryKovalev1EgorShulgin1PeterRichta´rik1AlexanderRogozin23AlexanderGasnikov23Abstract⇒⇒WeproposeADOM–anacceleratedmethodf...
AdaptiveNewtonSketch:Linear-timeOptimizationwithQuadraticConvergenceandEffectiveHessianDimensionalityJonathanLacotte1YifeiWang1MertPilanci1Abstract1.IntroductionWeproposearandomizedalgorithmwithWec...
AValue-Function-basedInterior-pointMethodforNon-convexBi-levelOptimizationRishengLiu123XuanLiu12XiaomingYuan4ShangzhiZeng4JinZhang56Abstractaremainlydividedintotwotypes,forinstance,hyper-parameters...
AsynchronousDecentralizedOptimizationWithImplicitStochasticVarianceReductionKentaNiwa12GuoqiangZhang3W.BastiaanKleijn4NoboruHarada12HiroshiSawada1AkinoriFujino1AbstractOurgoalistofacilitateMLmodelt...
AScalableDeterministicGlobalOptimizationAlgorithmforClusteringProblemsKaixunHua1MingfeiShi1YankaiCao1AbstractThedifferentdefinitionsofcostfunctioninducedifferenttypesofclusteringalgorithms.Inthispa...
TaylorExpansionPolicyOptimizationYunhaoTang1MichalValko2Re´miMunos2AbstractgorithmicideashavecontributedsignificantlytostabilizingpolicyOptimization.Inthiswork,weinvestigatetheapplicationofTaylore...
StochasticRank:GlobalOptimizationofScale-FreeDiscreteFunctionsAlekseiUstimenko1LiudmilaProkhorenkova123AbstractTodealwiththediscretestructureofarankingloss,onecanusesomesmoothapproximation,whichise...
StochasticOptimizationforNon-convexInf-ProjectionProblemsYanYan1YiXu2LiijunZhang3XiaoyuWang4TianbaoYang1AbstractX→Rmisalower-semicontinuousdifferentiablemapping,and·,·istheinnerproduct.Therequir...
StochasticOptimizationforRegularizedWassersteinEstimatorsMarinBallu1QuentinBerthet2FrancisBach3Abstractcantransportmasswithdistributionmeasureµtoanotherdistributionmeasureν,withminimalglobaltrans...
StochasticGauss-NewtonAlgorithmsforNonconvexCompositionalOptimizationQuocTran-Dinh1NhanH.Pham1LamM.Nguyen2Abstractandnpi=1,thenbyintroductingFi(x):=i=1WedeveloptwonewstochasticGauss-Newtonalgorithm...
StochasticFlowsandGeometricOptimizationontheOrthogonalGroupKrzysztofChoromanski12DavidCheikhi3JaredDavis1ValeriiLikhosherstov4AchilleNazaret3AchrafBahamou2XingyouSong1MrugankAkarte2JackParker-Holde...
SparseConvexOptimizationviaAdaptivelyRegularizedHardThresholdingKyriakosAxiotis1MaximSviridenko2Abstractlution(itsnumberofnon-zeroentries).Variantsandspecialcasesofthisproblemhavebeenstudiedformany...
Rate-DistortionOptimizationGuidedAutoencoderforIsometricEmbeddinginEuclideanLatentSpaceKeizoKato1JingZhou2TomotakeSasaki1AkiraNakagawa1AbstractmodelwithunivariateGaussianpriors(Kingma&Welling,2014)...
R2-B2:RecursiveReasoning-BasedBayesianOptimizationforNo-RegretLearninginGamesZhongxiangDai1YizhouChen1BryanKianHsiangLow1PatrickJaillet2Teck-HuaHo3Abstractadversarialmachinelearning(ML),theinteract...
ProvablyEfficientExplorationinPolicyOptimizationQiCai1ZhuoranYang2ChiJin3ZhaoranWang1Abstractofiterations,evengiveninfinitedata.Meanwhile,fromthestatisticalperspective,itremainsunclearhowtoattainWh...
ProjectivePreferentialBayesianOptimizationPetrusMikkola1MilicaTodorovic´2JariJa¨rvi2PatrickRinke2SamuelKaski13AbstractFigure1.Anillustrationofaprojectivepreferentialqueryonmolecularproperties:inw...
Projection-free√DistributedOnlineConvexOptimizationwithO(T)CommunicationComplexityYuanyuWan1Wei-WeiTu2LijunZhang1AbstractIncontrast,thelinearOptimizationstepinCGonlyrequirescomputingthetopsingular...