TrainLarge,ThenCompress:RethinkingModelSizeforEfficientTrainingandInferenceofTransformersZhuohanLi1EricWallace1ShengShen1KevinLin1KurtKeutzer1DanKlein1JosephE.Gonzalez1AbstractCommonTrainSmallStopT...
SmallData,BigDecisions:ModelSelectionintheSmall-DataRegimeJo¨rgBornschein1FrancescoVisin1SimonOsindero1Abstractformance(intermsoferror)whenappliedtoclassificationproblems,eventhoughthegeneralizati...
LearningandDataSelectioninBigDatasetsHosseinS.Ghadikolaei1HadiGhauch12CarloFischione1MikaelSkoglund1Abstractmodel.Studyingitsbehavioraroundthosecriticalsampleshelpsustobetterunderstandtheunknownmod...