Neural collapse with unconstrained features

R. A. Rankin, The closest packing of spherical caps in n n dimensions, In: Proceedings of the Glasgow Mathematical Association, vol. 2, Cambridge University Press, 1955, pp. 139–144

1955

Earlier work this paper cites.

T. Strohmer, R. W. Heath, Grassmannian frames with applications to coding and communication, Appl. Comput. Harmon. Anal. 14 (2003) 257–275

2003

Earlier work this paper cites.

J. M. Renes, R. Blume-Kohout, A. J. Scott, C. M. Caves, Symmetric informationally complete quantum measurements, J. Math. Phys. 45 (2004) 2171–2180

2004

Earlier work this paper cites.

A. Krizhevsky, I. Sutskever, G. Hinton, ImageNet Classification with Deep Convolutional Neural Networks, NIPS 2012, 1097–1105

2012

Earlier work this paper cites.

A. S. Bandeira, M. Fickus, D. G. Mixon, P. Wong, The road to deterministic matrices with the restricted isometry property, J. Fourier Anal. Appl. 19 (2013) 1123–1149

2013

Cited alongside, same era.

D. G. Mixon, C. J. Quinn, N. Kiyavash, M. Fickus, Fingerprinting with equiangular tight frames, IEEE Trans. Inf. Theory 59 (2013) 1855–1865

2013

Cited alongside, same era.

S. Arora, N. Cohen, E. Hazan, On the optimization of deep networks: Implicit acceleration by overparameterization, ICML 2018, 372–389

2018

Cited alongside, same era.

L. Chizat, F. Bach, On the global convergence of gradient descent for over-parameterized models using optimal transport, NeurIPS 2018, 3036–3046

2018

Cited alongside, same era.

M. Fickus, D. G. Mixon, Tables of the existence of equiangular tight frames, arXiv:1504.00253

Original

Cited in the paper.

D. P. Kingma, J. Ba, Adam: A method for stochastic optimization, arXiv:1412.6980

Original

Cited in the paper.

Multi-Layer Neural Network, UFLDL Tutorial, http://ufldl.stanford.edu/tutorial/supervised/MultiLayerNeuralNetworks/

Cited in the paper.

S. S. Du, W. Hu, J. D. Lee, Algorithmic regularization in learning deep homogeneous models: Layers are automatically balanced, NeurIPS 2018, 384–395

2018

Later among the works it cites.

S. S. Du, X. Zhai, B. Poczos, A. Singh, Gradient descent provably optimizes over-parameterized neural networks, ICLR 2018

2018

Later among the works it cites.

M. Song, A. Montanari, P. Nguyen, A mean field view of the landscape of two-layers neural networks.” Proc. Natl. Acad. Sci. U.S.A. 115 (2018) E7665–E7671

2018

Later among the works it cites.

V. Papyan, X. Y. Han, D. L. Donoho, Prevalence of neural collapse during the terminal phase of deep learning training, Proc. Natl. Acad. Sci. U.S.A. 117 (2020) 24652–24663

2020

Closest in time.