Fetching the paper…
Reading the bibliography…
We consider the neural ODE perspective of supervised learning and study the impact of the final time $T$ (which may indicate the depth of a corresponding ResNet) in training.
Universal flow approximation with deep residual networks
Müller, J. (2019) · 1910
Earlier work this paper cites.
Deep learning via dynamical systems: An approximation perspective
Li, Q., Lin, T., and Shen, Z. (2019) · 1912
Earlier work this paper cites.
A model of general economic equilibrium
von Neumann, J. (1945) · 1945
Earlier work this paper cites.
Linear Programming and Economic Analysis
Dorfman, R., Samuelson, P., and Solow, R. (1958) · 1958
Earlier work this paper cites.
Sur le problème de la division
Lojasiewicz, S. (1959) · 1959
Earlier work this paper cites.
Neural networks and physical systems with emergent collective computational abilities
Hopfield, J. J. (1982) · 1982
Earlier work this paper cites.
Semianalytic and subanalytic sets
Bierstone, E. and Milman, P. D. (1988) · 1988
Earlier work this paper cites.
A theoretical framework for back-propagation
LeCun, Y., Touresky, D., Hinton, G., and Sejnowski, T. (1988) · 1988
Earlier work this paper cites.
Approximation by superpositions of a sigmoidal function
Cybenko, G. (1989) · 1989
Earlier work this paper cites.
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., and White, H. (1989) · 1989
Earlier work this paper cites.
For neural networks, function determines form
Albertini, F. and Sontag, E. D. (1993) · 1993
Earlier work this paper cites.
Uniqueness of weights for neural networks
Albertini, F., Sontag, E. D., and Maillot, V. (1993) · 1993
Earlier work this paper cites.
Complete controllability of continuous-time recurrent neural networks
Sontag, E. and Sussmann, H. (1997) · 1997
Earlier work this paper cites.
Approximation theory of the MLP model in neural networks
Pinkus, A. (1999) · 1999
Earlier work this paper cites.
Further results on controllability of recurrent neural networks
Sontag, E. D. and Qiao, Y. (1999) · 1999
Earlier work this paper cites.
Functions of bounded variation and free discontinuity problems
Ambrosio, L., Fusco, N., and Pallara, D. (2000) · 2000
Earlier work this paper cites.
A rigorous framework for the mean field limit of multilayer neural networks
Nguyen, P.-M. and Pham, H. T. (2020) · 2001
Earlier work this paper cites.
Rademacher and Gaussian complexities: Risk bounds and structural results
Bartlett, P. L. and Mendelson, S. (2002) · 2002
Earlier work this paper cites.
Margin maximizing loss functions
Rosset, S., Zhu, J., and Hastie, T. (2003) · 2003
Earlier work this paper cites.
Global steady-state controllability of one-dimensional semilinear heat equations
Coron, J.-M. and Trélat, E. (2004) · 2004
Earlier work this paper cites.
Boosting as a regularized path to a maximum margin classifier
Rosset, S., Zhu, J., and Hastie, T. (2004) · 2004
Earlier work this paper cites.
Network size and weights size for memorization with two-layers neural networks
Bubeck, S., Eldan, R., Lee, Y. T., and Mikulincer, D. (2020a) · 2006
Earlier work this paper cites.
Structure preserving deep learning
Celledoni, E., Ehrhardt, M. J., Etmann, C., McLachlan, R. I., Owren, B., Schönlieb, C.-B., and Sherry, F. (2020) · 2006
Earlier work this paper cites.
Control and nonlinearity
Coron, J.-M. (2007) · 2007
Earlier work this paper cites.
Universal approximation power of deep neural networks via nonlinear control theory
Tabuada, P. and Gharesifard, B. (2020) · 2007
Earlier work this paper cites.
Controllability and observability of partial differential equations: some results and open problems
Zuazua, E. (2007) · 2007
Earlier work this paper cites.
Control on the manifolds of mappings as a setting for deep learning
Agrachev, A. and Sarychev, A. (2020) · 2008
Earlier work this paper cites.
Continuous-in-depth neural networks
Queiruga, A. F., Erichson, N. B., Taylor, D., and Mahoney, M. W. (2020) · 2008
Earlier work this paper cites.
A law of robustness for two-layers neural networks
Bubeck, S., Li, Y., and Nagaraj, D. (2020b) · 2009
Earlier work this paper cites.
Adaptivity with moving grids
Budd, C. J., Huang, W., and Russell, R. D. (2009) · 2009
Cited alongside, same era.
On the complexity of linear prediction: Risk bounds, margin bounds, and regularization
Kakade, S. M., Sridharan, K., and Tewari, A. (2009) · 2009
Cited alongside, same era.
Functional analysis, Sobolev spaces and partial differential equations
Brezis, H. (2010) · 2010
Cited alongside, same era.
Mnist handwritten digit database
LeCun, Y., Cortes, C., and Burges, C. (2010) · 2010
Cited alongside, same era.
Turnpike in Lipschitz-nonlinear optimal control
Esteve, C., Geshkovski, B., Pighin, D., and Zuazua, E. (2020) · 2011
Cited alongside, same era.
Turnpike properties in optimal control: An overview of discrete-time and continuous-time results
The implicit bias of gradient descent on separable data
Soudry, D., Hoffer, E., Nacson, M. S., Gunasekar, S., and Srebro, N. (2018) · 2018
Later among the works it cites.
Deep limits of residual neural networks
Thorpe, M. and van Gennip, Y. (2018) · 2018
Later among the works it cites.
Integral and measure-turnpike properties for infinite-dimensional optimal control systems
Trélat, E. and Zhang, C. (2018) · 2018
Later among the works it cites.
Deep learning as optimal control problems: Models and numerical methods
Benning, M., Celledoni, E., Ehrhardt, M. J., Owren, B., and Schönlieb, C.-B. (2019) · 2019
Later among the works it cites.
Residual flows for invertible generative modeling
Chen, R. T., Behrmann, J., Duvenaud, D. K., and Jacobsen, J.-H. (2019) · 2019
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Faulwasser, T. and Grüne, L. (2020) · 2011
Cited alongside, same era.
Imagenet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012) · 2012
Cited alongside, same era.
Universal approximation property of neural ordinary differential equations
Teshima, T., Tojo, K., Ikeda, M., Ishikawa, I., and Oono, K. (2020) · 2012
Cited alongside, same era.
Long time versus steady state optimal control
Porretta, A. and Zuazua, E. (2013) · 2013
Cited alongside, same era.
The nature of statistical learning theory
Vapnik, V. (2013) · 2013
Cited alongside, same era.
Adam: A method for stochastic optimization
Kingma, D. P. and Ba, J. (2014) · 2014
Cited alongside, same era.
The turnpike property in finite-dimensional nonlinear optimal control
Trélat, E. and Zuazua, E. (2015) · 2015
Cited alongside, same era.
Du, S., Lee, J., Li, H., Wang, L., and Zhai, X. (2019) · 2019
Later among the works it cites.
Augmented Neural ODEs
Dupont, E., Doucet, A., and Teh, Y. W. (2019) · 2019
Later among the works it cites.
Deep neural networks motivated by partial differential equations
Ruthotto, L. and Haber, E. (2019) · 2019
Later among the works it cites.
Regularization matters: Generalization and optimization of neural nets vs their induced kernel
Wei, C., Lee, J. D., Liu, Q., and Ma, T. (2019) · 2019
Later among the works it cites.
A mean-field optimal control formulation of deep learning
Weinan, E., Han, J., and Li, Q. (2019) · 2019
Later among the works it cites.
Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity
Yun, C., Sra, S., and Jadbabaie, A. (2019) · 2019
Later among the works it cites.
Neural ODEs as the deep limit of ResNets with constant weights
Avelin, B. and Nyström, K. (2020) · 2020
Closest in time.
Implicit bias of gradient descent for wide two-layer neural networks trained with the logistic loss
Chizat, L. and Bach, F. (2020) · 2020
Closest in time.
Deep neural networks, generic universal interpolation, and controlled ODEs
Cuchiero, C., Larsson, M., and Teichmann, J. (2020) · 2020
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.
Layer-parallel training of deep residual neural networks
Gunther, S., Ruthotto, L., Schroder, J. B., Cyr, E. C., and Gauger, N. R. (2020) · 2020
Closest in time.
Analysis of a two-layer neural network via displacement convexity
Javanmard, A., Mondelli, M., Montanari, A., et al. (2020) · 2020
Closest in time.
Selection dynamics for deep neural networks
Liu, H. and Markowich, P. (2020) · 2020
Closest in time.
Implicit regularization in nonconvex statistical estimation: Gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution
Ma, C., Wang, K., Chi, Y., and Chen, Y. (2020) · 2020
Closest in time.
Mean field analysis of neural networks: A law of large numbers
Sirignano, J. and Spiliopoulos, K. (2020) · 2020
Closest in time.
Approximation capabilities of neural ODEs and invertible residual networks
Zhang, H., Gao, X., Unterman, J., and Arodz, T. (2020) · 2020
Closest in time.
Deep learning: a statistical viewpoint
Bartlett, P. L., Montanari, A., and Rakhlin, A. (2021) · 2021
Closest in time.
On the turnpike to design of deep neural nets: Explicit depth bounds
Faulwasser, T., Hempel, A.-J., and Streif, S. (2021) · 2021
Closest in time.
Neural ODE control for classification, approximation and transport
Ruiz-Balet, D. and Zuazua, E. (2021) · 2021
Closest in time.
An introduction to deep generative modeling
Ruthotto, L. and Haber, E. (2021) · 2021
Closest in time.
Momentum residual neural networks
Sander, M. E., Ablin, P., Blondel, M., and Peyré, G. (2021) · 2021
Closest in time.
Sparse approximation in learning via neural ODEs
Yagüe, C. E. and Geshkovski, B. (2021) · 2021
Closest in time.
Understanding deep convolutional networks
Mallat, S. (2016) · 2065
Closest in time.