Joined 8 years ago
EDIT: found it! https://arxiv.org/pdf/1609.02907.pdf
Infinite wide networks are a newly active field and has recently shown some promising results, theoretically [1, 2] and empirically [3].
[1] https://arxiv.org/abs/2001.06931 [3] https://arxiv.org/abs/1806.07572 [2] https://ai.googleblog.com/2020/03/fast-and-easy-infinitely-w...
Another interesting and very related paper [2] that they fail to mention also shows improvement in training time (epochs) with dynamic pruning
And for the ones who wondered how far this is going back time I suggest you to read this one [3]
[1] https://www.nature.com/articles/s41467-018-04316-3
[2] https://arxiv.org/abs/1608.04493
[3] https://papers.nips.cc/paper/323-generalization-by-weight-el...
