On the emergence of simplex symmetry in the final and penultimate layers of neural network classifiers

Built on

On the global convergence of gradient descent for over-parameterized models using optimal transport
L. Chizat and F. Bach · 2018
Earlier work this paper cites.
The loss landscape of overparameterized neural networks
Original
Y. Cooper · 2018
Earlier work this paper cites.
Gradient descent finds global minima of deep neural networks
Original
S. S. Du, J. D. Lee, H. Li, L. Wang, and X. Zhai · 2018
Earlier work this paper cites.
Gradient descent provably optimizes over-parameterized neural networks
Original
S. S. Du, X. Zhai, B. Poczos, and A. Singh · 2018
Earlier work this paper cites.

Implicit bias of gradient descent for wide two-layer neural networks trained with the logistic loss
Original
L. Chizat and F. Bach · 2020
Cited alongside, same era.
A comparative analysis of optimization and generalization properties of two-layer neural network and random feature models under gradient descent dynamics
W. E, C. Ma, and L. Wu · 2020
Cited alongside, same era.
Another step toward demystifying deep neural networks
M. Elad, D. Simon, and A. Aberdam · 2020
Cited alongside, same era.
Neural collapse with cross-entropy loss
J. Lu and S. Steinerberger · 2020
Cited alongside, same era.

Neural collapse with unconstrained features
Original
D. G. Mixon, H. Parshall, and J. Pi · 2020
Closest in time.
Prevalence of neural collapse during the terminal phase of deep learning training
V. Papyan, X. Han, and D. L. Donoho · 2020
Closest in time.
On the global convergence of gradient descent training for two-layer Relu networks in the mean field regime
Original
S. Wojtowytsch · 2020
Closest in time.