2020
Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE.
Zhuang J, Dvornek N, Li X, Tatikonda S, Papademetris X, Duncan J. Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE. Proceedings Of Machine Learning Research 2020, 119: 11639-11649. PMID: 34308361, PMCID: PMC8299461.Peer-Reviewed Original ResearchNeural ordinary differential equationsComputation graphImage classification tasksClassification taskPyTorch implementationBenchmark tasksTraining timeAdaptive checkpointsNeural ODEAutomatic differentiationNaive methodTime series modelingRedundant componentsGradient estimation methodError rateGood accuracyPhysical knowledgeEmpirical performanceGraphGradient estimationTaskAccuracyODE solverSolverResNet
1997
Efficient Derivative Codes through Automatic Differentiation and Interface Contraction: An Application in Biostatistics
Hovland P, Bischof C, Spiegelman D, Casella M. Efficient Derivative Codes through Automatic Differentiation and Interface Contraction: An Application in Biostatistics. SIAM Journal On Scientific Computing 1997, 18: 1056-1066. DOI: 10.1137/s1064827595281800.Peer-Reviewed Original ResearchAutomatic differentiationDerivative codeInterface contractionHigh-level structureADIFOR (Automatic Differentiation of Fortran) toolEfficient codeNumber of variablesPerformance figuresComputation of derivativesCodeLittle effortComputationDivided difference approximationsJudicious fashionUsersCase studyChain ruleLikelihood functionErrorSubroutine
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply