Fetching the paper…
Reading the bibliography…
Many supervised learning problems involve high-dimensional data such as images, text, or graphs.
The accumulated distribution of quadratic forms on the sphere
N. C. Saldanha and C. Tomei · 1996
Earlier work this paper cites.
Regularization with dot-product kernels
A. J. Smola, Z. L. Ovari, and R. C. Williamson · 2001
Earlier work this paper cites.
On the mathematical foundations of learning
F. Cucker and S. Smale · 2002
Earlier work this paper cites.
Optimal rates for the regularized least-squares algorithm
A. Caponnetto and E. De Vito · 2007
Earlier work this paper cites.
Kernel methods for deep learning
Y. Cho and L. K. Saul · 2009
Earlier work this paper cites.
The elements of statistical learning: data mining, inference, and prediction
T. Hastie, R. Tibshirani, and J. Friedman · 2009
Earlier work this paper cites.
Spherical harmonics and approximations on the unit sphere: an introduction
K. Atkinson and W. Han · 2012
Earlier work this paper cites.
Group invariant scattering
S. Mallat · 2012
Earlier work this paper cites.
Invariant scattering convolution networks
J. Bruna and S. Mallat · 2013
Earlier work this paper cites.
Spherical harmonics in p dimensions
C. Efthimiou and C. Frye · 2014
Earlier work this paper cites.
Convolutional kernel networks
J. Mairal, P. Koniusz, Z. Harchaoui, and C. Schmid · 2014
Earlier work this paper cites.
Deep vs. shallow networks: An approximation theory perspective
H. N. Mhaskar and T. Poggio · 2016
Cited alongside, same era.
Breaking the curse of dimensionality with convex neural networks
F. Bach · 2017
Cited alongside, same era.
Inductive bias of deep convolutional networks through pooling geometry
N. Cohen and A. Shashua · 2017
Cited alongside, same era.
Why and when can deep-but not shallow-networks avoid the curse of dimensionality: a review
T. Poggio, H. Mhaskar, L. Rosasco, B. Miranda, and Q. Liao · 2017
Cited alongside, same era.
Generalization error of invariant classifiers
J. Sokolic, R. Giryes, G. Sapiro, and M. Rodrigues · 2017
Cited alongside, same era.
How many samples are needed to estimate a convolutional neural network?
S. S. Du, Y. Wang, X. Zhai, S. Balakrishnan, R. Salakhutdinov, and A. Singh · 2018
Sobolev norm learning rates for regularized least-squares algorithms
S. Fischer and I. Steinwart · 2020
Later among the works it cites.
Learning Theory from First Principles (draft)
F. Bach · 2021
Closest in time.
Approximation and learning with deep convolutional models: a kernel perspective
A. Bietti · 2021
Closest in time.
Deep equals shallow for ReLU networks in kernel regimes
A. Bietti and F. Bach · 2021
Closest in time.
Provably strict generalisation benefit for equivariant models
B. Elesedy and S. Zaidi · 2021
Closest in time.
Locality defeats the curse of dimensionality in convolutional teacher-student scenarios
A. Favero, F. Cagnetta, and M. Wyart · 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.
Statistical optimality of stochastic gradient descent on hard learning problems through multiple passes
L. Pillaud-Vivien, A. Rudi, and F. Bach · 2018
Cited alongside, same era.
Group invariance, stability to deformations, and complexity of deep convolutional representations
A. Bietti and J. Mairal · 2019
Cited alongside, same era.
Localized structured prediction
C. Ciliberto, F. Bach, and A. Rudi · 2019
Cited alongside, same era.
High-dimensional statistics: A non-asymptotic viewpoint
M. J. Wainwright · 2019
Cited alongside, same era.
Why are convolutional nets more sample-efficient than fully-connected nets?
Z. Li, Y. Zhang, and S. Arora · 2021
Closest in time.
Computational separation between convolutional and fully-connected networks
E. Malach and S. Shalev-Shwartz · 2021
Closest in time.
Learning with invariances in random features and kernel models
S. Mei, T. Misiakiewicz, and A. Montanari · 2021
Closest in time.
Relative stability toward diffeomorphisms indicates performance in deep nets
L. Petrini, A. Favero, M. Geiger, and M. Wyart · 2021
Closest in time.