Neural Tangent Kernel: Convergence and Generalization in Neural Networks (Invited Paper)

Jacot, ArthurGabriel, FranckHongler, Clement2022-07-182022-07-182022-07-182021-01-0110.1145/3406325.3465355https://infoscience.epfl.ch/handle/20.500.14299/189229WOS:000810492500004The Neural Tangent Kernel is a new way to understand the gradient descent in deep neural networks, connecting them with kernel methods. In this talk, I'll introduce this formalism and give a number of results on the Neural Tangent Kernel and explain how they give us insight into the dynamics of neural networks during training and into their generalization features.Computer Science, Theory & MethodsOperations Research & Management ScienceMathematics, AppliedComputer ScienceMathematicsneural tangent kernelNeural Tangent Kernel: Convergence and Generalization in Neural Networks (Invited Paper)text::conference output::conference proceedings::conference paper