Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel

Stanislav Fort, Gintare Karolina Dziugaite, Mansheej Paul, Sepideh Kharaghani, Daniel M. Roy 0001, Surya Ganguli. Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel. In Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, Hsuan-Tien Lin, editors, Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual. 2020. [doi]

@inproceedings{FortDPK0G20,
  title = {Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel},
  author = {Stanislav Fort and Gintare Karolina Dziugaite and Mansheej Paul and Sepideh Kharaghani and Daniel M. Roy 0001 and Surya Ganguli},
  year = {2020},
  url = {https://proceedings.neurips.cc/paper/2020/hash/405075699f065e43581f27d67bb68478-Abstract.html},
  researchr = {https://researchr.org/publication/FortDPK0G20},
  cites = {0},
  citedby = {0},
  booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual},
  editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria-Florina Balcan and Hsuan-Tien Lin},
}