DissectingSupervisedConstrastiveLearningFlorianGraf1ChristophD.Hofer1MarcNiethammer2RolandKwitt1AbstractInthisconstruction,fisrealizedasthecompositionofanencoderϕ:X→Z⊆Rh,alinearmap/classifierMin...
DissectingNon-VacuousGeneralizationBoundsbasedontheMean-FieldApproximationKonstantinosPitas1Abstract(a)Explaininghowoverparametrizedneuralnet-Figure1.Risk-ComplexityplotforMNIST10:Theareabelowworks...
DissectingAdam:TheSign,MagnitudeandVarianceofStochasticGradientsLukasBalles1PhilippHennig1AbstractwhichisarandomvariablewithE[g(θ)]=∇L(θ).Animportantquantityforthispaperwillbethe(element-wise)Th...