@misc{dl2-a01-1,
  title={Neural Tangent Kernel: Convergence and Generalization in Neural Networks},
  author={Arthur Jacot, Franck Gabriel, Clément Hongler},
  year={2018},
  url={https://arxiv.org/abs/1806.07572}
}
@misc{dl2-a01-2,
  title={Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent},
  author={Jaehoon Lee, Lechao Xiao, Samuel S. Schoenholz, Yasaman Bahri, Roman Novak, Jascha Sohl-Dickstein, Jeffrey Pennington},
  year={2019},
  url={https://arxiv.org/abs/1902.06720}
}
@misc{dl2-a01-3,
  title={On Lazy Training in Differentiable Programming},
  author={Lénaïc Chizat, Edouard Oyallon, Francis Bach},
  year={2019},
  url={https://arxiv.org/abs/1812.07956}
}
@misc{dl2-a01-4,
  title={Tensor Programs II: Neural Tangent Kernel for Any Architecture},
  author={Greg Yang},
  year={2020},
  url={https://arxiv.org/abs/2006.14548}
}
@misc{dl2-a01-5,
  title={Feature Learning in Infinite-Width Neural Networks},
  author={Greg Yang, Edward J. Hu},
  year={2021},
  url={https://arxiv.org/abs/2011.14522}
}
@misc{dl2-a01-6,
  title={On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport},
  author={Lénaïc Chizat, Francis Bach},
  year={2018},
  url={https://arxiv.org/abs/1805.09545}
}