OnthePredictabilityofPruningAcrossScalesJonathanRosenfeld1JonathanFrankle1MichaelCarbin1NirShavit1AbstractAsafirsttry,wecouldattempttoanswerthisquestionusingbruteforce:wecouldpruneeverymemberofanet...
ImprovingPredictorsviaCombinationAcrossDiverseTaskCategoriesKwangInKim1AbstractPredictorcombinationisrelatedtomulti-tasklearning(MTL)andtransferlearning(TL).However,sincenoaccessPredictorcombinatio...
CLOCS:ContrastiveLearningofCardiacSignalsAcrossSpace,Time,andPatientsDaniKiyasseh1TingtingZhu1DavidA.Clifton12Abstractsharesomecontext.Bycapturingthishigh-levelsharedcontext(e.g.,medicaldiagnosis),...
FeatureNoiseInducesLossDiscrepancyAcrossGroupsFereshteKhani1PercyLiang1Abstractdiscrepancy(Liptonetal.,2018)andadverselong-termimpacts(Liuetal.,2018).Therefore,itisimportanttoTheperformanceofstanda...
SeparatingvaluefunctionsAcrosstime-scalesJoshuaRomoff12PeterHenderson3AhmedTouati42EmmaBrunskill3JoellePineau12YannOllivier2Abstractvergenceproperties,makinglearningmoreefficientandstable(Bertsekas...
LearningGenerativeModelsAcrossIncomparableSpacesCharlotteBunne1DavidAlvarez-Melis2AndreasKrause1StefanieJegelka2Abstractof28×28-pixelvectorsforMNIST),andthegenerateddis-tributionthatminimizestheob...
DeepModelsofInteractionsAcrossSetsJasonHartford1DevonRGraham1KevinLeyton-Brown1SiamakRavanbakhsh1AbstractR.ThecanonicalrepresentationofsuchafunctionisamatrixX∈RN×M;ofcourse,wewantXn,m=xforeachWeu...