Fetching the paper…
Reading the bibliography…
We build on the dynamical systems approach to deep learning, where deep residual networks are idealized as continuous-time dynamical systems, from the approximation perspective.
Error bounds for approximations with deep relu neural networks in w s , p w^{s,p} norms
Gühring, I., Kutyniok, G., and Petersen, P. (2019) · 1902
Earlier work this paper cites.
Predict globally, correct locally: Parallel-in-time optimal control of neural networks
Parpas, P. and Muir, C. (2019) · 1902
Earlier work this paper cites.
Nonlinear approximation via compositions
Shen, Z., Yang, H., and Zhang, S. (2019b) · 1902
Earlier work this paper cites.
A Priori Estimates of the Population Risk for Residual Networks
E, W., Ma, C., and Wang, Q. (2019b) · 1903
Earlier work this paper cites.
Dupont, E., Doucet, A., and Teh, Y. W. (2019) · 1904
Earlier work this paper cites.
Nonlinear approximation and (deep) relu networks
Daubechies, I., DeVore, R., Foucart, S., Hanin, B., and Petrova, G. (2019) · 1905
Earlier work this paper cites.
Selection dynamics for deep neural networks
Liu, H. and Markowich, P. (2019) · 1905
Earlier work this paper cites.
You only propagate once: Painless adversarial training using maximal principle
Zhang, D., Zhang, T., Lu, Y., Zhu, Z., and Dong, B. (2019a) · 1905
Earlier work this paper cites.
Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View
Lu, Y., Li, Z., He, D., Sun, Z., Dong, B., Qin, T., Wang, L., and Liu, T.-Y. (2019) · 1906
Earlier work this paper cites.
Barron spaces and the compositional function spaces for neural network models
Ma, C., Wu, L., et al. (2019) · 1906
Earlier work this paper cites.
Approximation capabilities of neural ordinary differential equations
Zhang, H., Gao, X., Unterman, J., and Arodz, T. (2019b) · 1907
Earlier work this paper cites.
Note on the Derivatives with Respect to a Parameter of the Solutions of a System of Differential Equations
Gronwall, T. H. (1919) · 1919
Earlier work this paper cites.
The embedding of homeomorphisms in flows
Fort, M. K. (1955) · 1955
Earlier work this paper cites.
Relaxed variational problems
Warga, J. (1962) · 1962
Earlier work this paper cites.
Ordinary differential equations
Arnold, V. I. (1973) · 1973
Earlier work this paper cites.
Vector fields generate few diffeomorphisms
Palis, J. (1974) · 1974
Earlier work this paper cites.
The embedding of homeomorphisms in continuous flows
Utz, W. (1981) · 1981
Earlier work this paper cites.
Controllability questions for nonlinear systems in abstract spaces
Chukwu, E. N. and Lenhart, S. M. (1991) · 1991
Earlier work this paper cites.
Ten lectures on wavelets
Daubechies, I. (1992) · 1992
Cited alongside, same era.
Affine systems inl2 (rd): the analysis of the analysis operator
Ron, A. and Shen, Z. (1997) · 1997
Cited alongside, same era.
Nonlinear approximation
DeVore, R. A. (1998) · 1998
Cited alongside, same era.
A wavelet tour of signal processing
Mallat, S. (1999) · 1999
Cited alongside, same era.
Algebraic topology
Hatcher, A. (2000) · 2000
Cited alongside, same era.
Controllability of nonlinear systems in Banach spaces: A survey
Balachandran, K. and Dauer, J. P. (2002) · 2002
Cited alongside, same era.
l p l^{p} approximation of maps by diffeomorphisms
Brenier, Y. and Gangbo, W. (2003) · 2003
Reversible architectures for arbitrarily deep residual neural networks
Chang, B., Meng, L., Haber, E., Ruthotto, L., Begert, D., and Holtham, E. (2018) · 2018
Later among the works it cites.
Neural ordinary differential equations
Chen, T. Q., Rubanova, Y., Bettencourt, J., and Duvenaud, D. K. (2018) · 2018
Later among the works it cites.
Maximum Principle Based Algorithms for Deep Learning
Li, Q., Chen, L., Tai, C., and E, W. (2018) · 2018
Later among the works it cites.
An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks
Li, Q. and Hao, S. (2018) · 2018
Later among the works it cites.
Resnet with one-neuron hidden layers is a universal approximator
Lin, H. and Jegelka, S. (2018) · 2018
Later among the works it cites.
Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
Finite Difference Methods for Ordinary and Partial Differential Equations: Steady-State and Time-Dependent Problems
Leveque, R. J. (2007) · 2007
Cited alongside, same era.
Embedding diffeomorphisms in flows in banach spaces
Zhang, X. (2009) · 2009
Cited alongside, same era.
Deep residual learning for image recognition
He, K., Zhang, X., Ren, S., and Sun, J. (2016) · 2016
Cited alongside, same era.
Residual networks behave like ensembles of relatively shallow networks
Veit, A., Wilber, M. J., and Belongie, S. (2016) · 2016
Cited alongside, same era.
Multi-level residual networks from dynamical systems view
Chang, B., Meng, L., Haber, E., Tung, F., and Begert, D. (2017) · 2017
Cited alongside, same era.
Lu, Y., Zhong, A., Li, Q., and Dong, B. (2018) · 2018
Later among the works it cites.
Deep neural networks motivated by partial differential equations
Ruthotto, L. and Haber, E. (2018) · 2018
Later among the works it cites.
Stochastic training of residual networks: a differential equation viewpoint
Sun, Q., Tao, Y., and Du, Q. (2018) · 2018
Later among the works it cites.
Nonlocal neural networks, nonlocal diffusion and nonlocal modeling
Tao, Y., Sun, Q., Du, Q., and Liu, W. (2018) · 2018
Later among the works it cites.
Enresnet: Resnet ensemble via the feynman-kac formalism
Wang, B., Yuan, B., Shi, Z., and Osher, S. J. (2018) · 2018
Later among the works it cites.
Monge-Ampere Flow for Generative Modeling
Zhang, L. and Wang, L. (2018) · 2018
Later among the works it cites.
Dynamically unfolding recurrent restorer: A moving endpoint control method for image restoration
Zhang, X., Lu, Y., Liu, J., and Dong, B. (2018) · 2018
Later among the works it cites.
Deep distributed convolutional neural networks: Universality
Zhou, D.-X. (2018) · 2018
Later among the works it cites.
Approximation analysis of convolutional neural networks
Bao, C., Li, Q., Tai, C., Wu, L., and Xiang, X. (2019) · 2019
Closest in time.
Deep approximation of functions by composition
Li, Q., Shen, Z., and Tai, C. (2019) · 2019
Closest in time.
Transport analysis of infinitely deep neural network
Sonoda, S. and Murata, N. (2019) · 2019
Closest in time.
Variational networks: An optimal control approach to early stopping variational methods for image restoration
Effland, A., Kobler, E., Kunisch, K., and Pock, T. (2020) · 2020
Closest in time.
Understanding deep convolutional networks
Mallat, S. (2016) · 2065
Closest in time.