Litcius/Paper detail

A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions

Patrick Cheridito, Arnulf Jentzen, Adrian Riekert, Florian Rossmannek

2022Journal of Complexity25 citationsDOIOpen Access PDF

Topics & Concepts

Gradient descentArtificial neural networkConstant (computer programming)Lyapunov functionConstant functionConvergence (economics)MathematicsFunction (biology)ConjectureActivation functionApplied mathematicsFeedforward neural networkFeed forwardMathematical optimizationComputer scienceArtificial intelligenceMathematical analysisDiscrete mathematicsNonlinear systemEngineeringQuantum mechanicsProgramming languageBiologyEconomic growthControl engineeringPhysicsEvolutionary biologyEconomicsPiecewiseStochastic Gradient Optimization TechniquesSparse and Compressive Sensing TechniquesNeural Networks and Applications
A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions | Litcius