Any Target Function Exists in a Neighborhood of Any Sufficiently Wide Random Network: A Geometrical Perspective

Karakida, R., Akaho, S., Amari, S., The normalization method for alleviating pathological sharpness in wide neural networks. 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada, arXiv:1906.02926, (2019b)

Original

1906

Earlier work this paper cites.

Rozonoer, L.I., Random logical nets, I, II, III. Avtomatika I Telemekhanica, nos. 5, 6, 7, 137–147, 99–109, 127–136, (1969)

1969

Earlier work this paper cites.

Amari, S., Characteristics of randomly connected threshold-element networks and network systems. Proc. IEEE., 59, 1, 35–47, (1971)

1971

Earlier work this paper cites.

Amari, S., A method of statistical neurodynamics. Kybernetik, 14, 201–215, (1974)

1974

Earlier work this paper cites.

Amari, S., Yoshida, K., Kanatani, K., A Mathematical foundation for statistical neurodynamics. SIAM J. Appl. Math., 33, 95–126, (1977)

1977

Earlier work this paper cites.

Amari, S., Ando, H., Toyoizumi, T., Masuda, N., State concentration exponent as a measure of quickness in Kauffman-type networks, Physical Review, E 87, 022814, (2013)

2013

Earlier work this paper cites.

Sompolinsky, H., Cristanti, A., Sommers, H. J., Chaos in random neural networks. Physical Review, E91, 032802, (2015)

2015

Earlier work this paper cites.

Poole, B., Lahiri, S., Raghu, M., Sohl-Dickstein, J., Ganguli, S., Exponential expressivity in deep neural network through transient chaos. in Advances in Neural Information Processing (NIPS), 3360–3368, (2016)

2016

Earlier work this paper cites.

Schoenholz, S.S., Gilmer, J,, Ganguli, S., Sohl-Dickstein, J., Deep information propagation. ICLR’2017, arXiv: 1611.01232, (2016)

2016

Cited alongside, same era.

Jacot, A., Gabriel, F., Hongler, C., Neural tangent kernel: Convergence and generalization in neural networks. Neurips 2018, arXiv:1806.07572v3, (2018)

Original

2018

Cited alongside, same era.

Sonoda, S., Ishikawa, I., Ikeda, M., Hagihara, K., Sawano, Y., Matsubara, T., Murata, N., The global optimum of shallow neural network is attained by ridgelet transform. arXiv:1805.07517, (2018)

Original

2018

Cited alongside, same era.

Allen-Zhu, Z., Li, Y., Liang, Y., Learning and generalization in overparameterized neural networks, going beyond two layers. arXiv:1811.04918v2, (2019)

Original

2019

Cited alongside, same era.

Belkin, M., Hsu, D., Xu, J., Two models of double descent for weak feature. arXiv:1903.07571v1, (2019)

Original

2019

Later among the works it cites.

Cai, T., Gao, R., Hou, J., Chen, S., Wong, D., He, D., Zhang, Z., Wang, L., A Gram-Gauss-Newton method learning overparametrized deep neural networks for regression problems. arXiv:1905.11675v1, (2019)

Original

2019

Later among the works it cites.

Cao, Y., Gu, Q., Generalization bounds of stochastic gradient descent for wide and deep neural networks. arXiv:1905.13210v3, NeurIPS, 2019

Original

2019

Later among the works it cites.

Karakida, R., Akaho, S., Amari, S., Universal statistics of Fisher information in deep neural networks: Mean field approach. AISTATS, 2019; arXiv:1806.01316v2, (2019a)

Original

2019

Later among the works it cites.