Feature-Learning Networks Are Consistent Across Widths At Realistic Scales

Nikhil Vyas 0001, Alexander Atanasov, Blake Bordelon, Depen Morwani, Sabarish Sainathan, Cengiz Pehlevan. Feature-Learning Networks Are Consistent Across Widths At Realistic Scales. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, Sergey Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023. 2023. [doi]

@inproceedings{0001ABMSP23,
  title = {Feature-Learning Networks Are Consistent Across Widths At Realistic Scales},
  author = {Nikhil Vyas 0001 and Alexander Atanasov and Blake Bordelon and Depen Morwani and Sabarish Sainathan and Cengiz Pehlevan},
  year = {2023},
  url = {http://papers.nips.cc/paper_files/paper/2023/hash/03600ae6c3392fd65ad7c3a90c6f7ce8-Abstract-Conference.html},
  researchr = {https://researchr.org/publication/0001ABMSP23},
  cites = {0},
  citedby = {0},
  booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
  editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
}