Fetching the paper…
Reading the bibliography…
Exploiting symmetry in dynamical systems is a powerful way to improve the generalization of deep learning.
Introduction to statistical learning theory
Bousquet, O., Boucheron, S., and Lugosi, G · 2003
Earlier work this paper cites.
Approximation error bounds via rademacher complexity
Gnecco, G. and Sanguineti, M · 2008
Earlier work this paper cites.
Statistical learning and sequential prediction
Rakhlin, A. and Sridharan, K · 2014
Earlier work this paper cites.
The effectiveness of data augmentation in image classification using deep learning
Perez, L. and Wang, J · 2017
Earlier work this paper cites.
Learning to compose domain-specific transformations for data augmentation
Ratner, A. J., Ehrenberg, H. R., Hussain, Z., Dunnmon, J., and Ré, C · 2017
Earlier work this paper cites.
Spherical CNNs
Cohen, T. S., Geiger, M., K ohler, J., and Welling, M · 2018
Earlier work this paper cites.
A kernel theory of modern data augmentation
Dao, T., Gu, A., Ratner, A., Smith, V., De Sa, C., and Ré, C · 2019
Earlier work this paper cites.
Improving robustness without sacrificing accuracy with patch gaussian augmentation
Lopes, R. G., Yin, D., Poole, B., Gilmer, J., and Cubuk, E. D · 2019
Earlier work this paper cites.
Does data augmentation lead to positive margin?
Rajput, S., Feng, Z., Charles, Z., Loh, P.-L., and Papailiopoulos, D · 2019
Cited alongside, same era.
A survey on image data augmentation for deep learning
Shorten, C. and Khoshgoftaar, T. M · 2019
Cited alongside, same era.
General E(2)-equivariant steerable CNNs
Weiler, M. and Cesa, G · 2019
Cited alongside, same era.
Deep scale-spaces: Equivariance over scale
Worrall, D. and Welling, M · 2019
Cited alongside, same era.
A group-theoretic framework for data augmentation
Chen, S., Dobriban, E., and Lee, J · 2020
Cited alongside, same era.
Discrepancy-based theory and algorithms for forecasting non-stationary time series
Kuznetsov, V. and Mohri, M · 2020
Cited alongside, same era.
Residual pathway priors for soft equivariance constraints
Finzi, M. A., Benton, G., and Wilson, A. G · 2021
Later among the works it cites.
Learning equivariances and partial equivariances from data
Romero, D. W. and Lohit, S · 2021
Later among the works it cites.
Improved generalization bounds of group invariant/equivariant deep networks via quotient feature spaces
Sannai, A., Imaizumi, M., and Kawano, M · 2021
Later among the works it cites.
Learning gradient fields for molecular conformation generation
Shi, C., Luo, S., Xu, M., and Tang, J · 2021
Later among the works it cites.
Relaxing equivariance constraints with non-stationary continuous filters
van der Ouderaa, T. F., Romero, D. W., and van der Wilk, M · 2022
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Wen, Q., Sun, L., Yang, F., Song, X., Gao, J., Wang, X., and Xu, H · 2020
Cited alongside, same era.
Geometric deep learning: Grids, groups, graphs, geodesics, and gauges
Bronstein, M. M., Bruna, J., Cohen, T., and Veličković, P · 2021
Cited alongside, same era.
Group equivariant convolutional networks
Cohen, T. S. and Welling, M
Cited in the paper.
Cohen, T. S. and Welling, M
Cited in the paper.
Data augmentation instead of explicit regularization
Hernández-García, A. and König, P
Cited in the paper.
Further advantages of data augmentation on convolutional neural networks
Hernández-García, A. and König, P
Cited in the paper.
Wang, R., Walters, R., and Yu, R · 2022
Closest in time.
Do deep networks transfer invariances across classes?
Zhou, A., Tajwar, F., Robey, A., Knowles, T., Pappas, G. J., Hassani, H., and Finn, C · 2022
Closest in time.