Fetching the paper…
Reading the bibliography…
We consider the neural ODE and optimal control perspective of supervised learning, with $\ell^1$-control penalties, where rather than only minimizing a final cost (the \emph{empirical risk}) for the state, we integrate this cost over the entire time horizon.
Linear inversion of band-limited reflection seismograms
Santosa, F., and Symes, W · 1986
Earlier work this paper cites.
Regression shrinkage and selection via the lasso
Tibshirani, R · 1996
Earlier work this paper cites.
On L 1 L^{1} -minimization in optimal control and applications to robotics
Vossen, G., and Maurer, H · 2006
Earlier work this paper cites.
Real analysis: theory of measure and integration second edition
Yeh, J · 2006
Earlier work this paper cites.
Switching control
Zuazua, E · 2010
Earlier work this paper cites.
Sparse stabilization and optimal control of the Cucker-Smale model
Caponigro, M., Fornasier, M., Piccoli, B., and Trélat, E · 2013
Earlier work this paper cites.
Mean-field sparse optimal control
Fornasier, M., Piccoli, B., and Rossi, F · 2014
Earlier work this paper cites.
Linear-quadratic control problems with L 1 L^{1} -control cost
Alt, W., and Schneider, C · 2015
Earlier work this paper cites.
Sparse stabilization and control of alignment models
Caponigro, M., Fornasier, M., Piccoli, B., and Trélat, E · 2015
Earlier work this paper cites.
The turnpike property in finite-dimensional nonlinear optimal control
Trélat, E., and Zuazua, E · 2015
Earlier work this paper cites.
Deep learning
Goodfellow, I., Bengio, Y., and Courville, A · 2016
Earlier work this paper cites.
Deep residual learning for image recognition
He, K., Zhang, X., Ren, S., and Sun, J · 2016
Earlier work this paper cites.
Understanding deep convolutional networks
Mallat, S · 2016
Earlier work this paper cites.
A proposal on machine learning via dynamical systems
E, W · 2017
Earlier work this paper cites.
Exact turnpike properties and economic nmpc
Faulwasser, T., and Bonvin, D · 2017
Earlier work this paper cites.
Stable architectures for deep neural networks
Haber, E., and Ruthotto, L · 2017
Earlier work this paper cites.
Infinite horizon sparse optimal control
Kalise, D., Kunisch, K., and Rao, Z · 2017
Cited alongside, same era.
Maximum principle based algorithms for deep learning
Li, Q., Chen, L., Tai, C., and E, W · 2017
Cited alongside, same era.
Neural ordinary differential equations
Chen, T. Q., Rubanova, Y., Bettencourt, J., and Duvenaud, D. K · 2018
Cited alongside, same era.
On the global convergence of gradient descent for over-parameterized models using optimal transport
Chizat, L., and Bach, F · 2018
Cited alongside, same era.
Large margin deep networks for classification
Elsayed, G., Krishnan, D., Mobahi, H., Regan, K., and Bengio, S · 2018
Cited alongside, same era.
Ffjord: Free-form continuous dynamics for scalable reversible generative models
Grathwohl, W., Chen, R. T., Bettencourt, J., Sutskever, I., and Duvenaud, D · 2018
On the turnpike to design of deep neural nets: Explicit depth bounds
Faulwasser, T., Hempel, A.-J., and Streif, S · 2021
Closest in time.
Control in moving interfaces and deep learning
Geshkovski, B · 2021
Closest in time.
The finite-time turnpike phenomenon for optimal control problems: Stabilization by non-smooth tracking terms
Gugat, M., Schuster, M., and Zuazua, E · 2021
Closest in time.
Normalizing flows for probabilistic modeling and inference
Papamakarios, G., Nalisnick, E. T., Rezende, D. J., Mohamed, S., and Lakshminarayanan, B · 2021
Closest in time.
Neural ODE control for classification, approximation and transport
Ruiz-Balet, D., and Zuazua, E · 2021
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
Deep learning as optimal control problems: Models and numerical methods
Benning, M., Celledoni, E., Ehrhardt, M. J., Owren, B., and Schönlieb, C.-B · 2019
Cited alongside, same era.
Augmented Neural ODEs
Dupont, E., Doucet, A., and Teh, Y. W · 2019
Cited alongside, same era.
Sensitivity analysis of optimal control for a class of parabolic PDEs motivated by model predictive control
Grüne, L., Schaller, M., and Schiela, A · 2019
Cited alongside, same era.
Latent ordinary differential equations for irregularly-sampled time series
Rubanova, Y., Chen, R. T., and Duvenaud, D. K · 2019
Cited alongside, same era.
Optimal approximation with sparsely connected deep neural networks
Bölcskei, H., Grohs, P., Kutyniok, G., and Petersen, P · 2020
Cited alongside, same era.
Variational networks: An optimal control approach to early stopping variational methods for image restoration
Effland, A., Kobler, E., Kunisch, K., and Pock, T · 2020
Cited alongside, same era.
Understanding deep learning (still) requires rethinking generalization
Zhang, C., Bengio, S., Hardt, M., Recht, B., and Vinyals, O · 2021
Closest in time.
Turnpike in Lipschitz—nonlinear optimal control
Esteve-Yagüe, C., Geshkovski, B., Pighin, D., and Zuazua, E · 2022
Closest in time.
Turnpike properties in optimal control
Faulwasser, T., and Grüne, L · 2022
Closest in time.
Optimal actuator design via Brunovsky’s normal form
Geshkovski, B., and Zuazua, E · 2022
Closest in time.
Turnpike in optimal control of PDEs, ResNets, and beyond
Geshkovski, B., and Zuazua, E · 2022
Closest in time.
On neural differential equations
Kidger, P · 2022
Closest in time.
Deep learning via dynamical systems: An approximation perspective
Li, Q., Lin, T., and Shen, Z · 2022
Closest in time.
Interpolation and approximation via momentum ResNets and neural ODEs
Ruiz-Balet, D., Affili, E., and Zuazua, E · 2022
Closest in time.
Universal approximation power of deep residual neural networks through the lens of control
Tabuada, P., and Gharesifard, B · 2022
Closest in time.
Learning polymorphic Neural ODEs with time-evolving mixture
Yoon, T., Shin, S., and Yang, E · 2022
Closest in time.