Fetching the paper…
Reading the bibliography…
We describe a general framework -- compressive statistical learning -- for resource-efficient large-scale learning: the training collection is compressed in one pass into a low-dimensional sketch (a vector of random empirical generalized moments) that captures the information relevant to the considered learning task.
On a theorem of Weyl concerning eigenvalues of linear transformations: I
K. Fan · 1949
Earlier work this paper cites.
The empirical characteristic function and its applications
A. Feuerverger and R. A. Mureika · 1977
Earlier work this paper cites.
The complexity of the generalized Lloyd - Max problem
M. R. Garey, D. S. Johnson, and H. S. Witsenhausen · 1982
Earlier work this paper cites.
Moments in Mathematics
H. J. Landau · 1987
Earlier work this paper cites.
Elements of Information Theory
T. M. Cover and J. A. Thomas · 1991
Earlier work this paper cites.
An approach to inequalities for the distributions of infinite-dimensional martingales
I. Pinelis · 1992
Earlier work this paper cites.
Large sample estimation and hypothesis testing
W. K. Newey and D. McFadden · 1994
Earlier work this paper cites.
Generalization of gmm to a continuum of moment conditions
M. Carrasco and J.-P. Florens · 2000
Earlier work this paper cites.
Efficient GMM estimation using the empirical characteristic function
M. Carrasco and J.-P. Florens · 2002
Earlier work this paper cites.
Real Analysis and Probability
R. M. Dudley · 2002
Earlier work this paper cites.
How to summarize the universe: dynamic maintenance of quantiles
A. C. Gilbert, Y. Kotidis, S. Muthukrishnan, and M. J. Strauss · 2002
Earlier work this paper cites.
Dynamic multidimensional histograms
N. Thaper, S. Guha, P. Indyk, and N. Koudas · 2002
Earlier work this paper cites.
Online expectation-maximization type algorithms for parameter estimation in general state space models
C. Andrieu and A. Doucet · 2003
Earlier work this paper cites.
Coresets for k k -means and k k -median clustering and their applications
S. Har-Peled and S. Mazumdar · 2004
Earlier work this paper cites.
Local Rademacher complexities
P. L. Bartlett, O. Bousquet, S. Mendelson, et al · 2005
Earlier work this paper cites.
An improved data stream summary: the count-min sketch and its applications
G. Cormode and S. Muthukrishnan · 2005
Earlier work this paper cites.
A fast k k -means implementation using coresets
G. Frahling and C. Sohler · 2005
Earlier work this paper cites.
Generalized Method of Moments
A. R. Hall · 2005
Earlier work this paper cites.
On the eigenspectrum of the Gram matrix and the generalization error of kernel-pca
J. Shawe-Taylor, C. K. Williams, N. Cristianini, and J. Kandola · 2005
Earlier work this paper cites.
Stable signal recovery from incomplete and inaccurate measurements
E. J. Candès, J. Romberg, and T. Tao · 2006
Earlier work this paper cites.
Compressed sensing
D. L. Donoho · 2006
Earlier work this paper cites.
Local Rademacher complexities and oracle inequalities in risk minimization
V. Koltchinskii · 2006
Earlier work this paper cites.
k-means++: the advantages of careful seeding
D. Arthur and S. Vassilvitskii · 2007
Earlier work this paper cites.
Compressive sensing
R. Baraniuk · 2007
Earlier work this paper cites.
Statistical properties of kernel principal component analysis
G. Blanchard, O. Bousquet, and L. Zwald · 2007
Earlier work this paper cites.
A kernel method for the two-sample problem
A. Gretton, K. M. Borgwardt, M. J. Rasch, B. Schölkopf, and A. J. Smola · 2007
Earlier work this paper cites.
Concentration Inequalities and Model Selection , volume 1896 of Lecture Notes in Mathematics
P. Massart · 2007
Earlier work this paper cites.
Random features for large scale kernel machines
A. Rahimi and B. Recht · 2007
Earlier work this paper cites.
A Hilbert space embedding for distributions
A. J. Smola, A. Gretton, L. Song, and B. Schölkopf · 2007
Cited alongside, same era.
A simple proof of the restricted isometry property for random matrices
R. Baraniuk, M. Davenport, R. A. DeVore, and M. B. Wakin · 2008
Cited alongside, same era.
The restricted isometry property and its implications for compressed sensing
E. J. Candès · 2008
Cited alongside, same era.
Streaming k k -means approximation
N. Ailon, R. Jaiswal, and C. Monteleoni · 2009
Cited alongside, same era.
NP-hardness of Euclidean sum-of-squares clustering
D. Aloise, A. Deshpande, P. Hansen, and P. Popat · 2009
Cited alongside, same era.
Online EM algorithm for latent data models
O. Cappé and E. Moulines · 2009
Cited alongside, same era.
Polynomial learning of distribution families
M. Belkin and K. Sinha · 2015
Later among the works it cites.
New analysis of manifold embeddings and signal recovery from compressive measurements
A. Eftekhari and M. B. Wakin · 2015
Later among the works it cites.
Sketching for large-scale learning of mixture models
N. Keriven, A. Bourrier, R. Gribonval, and P. Pérèz · 2015
Later among the works it cites.
Generative moment matching networks
Y. Li, K. Swersky, and R. Zemel · 2015
Later among the works it cites.
Less is more: Nyström computational regularization
A. Rudi, R. Camoriano, and L. Rosasco · 2015
Later among the works it cites.
Optimal rates for random fourier features
B. K. Sriperumbudur and Z. Szabó · 2015
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Compressed sensing and best k k -term approximation
A. Cohen, W. Dahmen, and R. DeVore · 2009
Cited alongside, same era.
Methods for finding frequent items in data streams
G. Cormode and M. Hadjieleftheriou · 2009
Cited alongside, same era.
Weighted sums of random kitchen sinks: Replacing minimization with randomization in learning
A. Rahimi and B. Recht · 2009
Cited alongside, same era.
Coresets and sketches for high dimensional subspace approximation problems
D. Feldman, M. Monemizadeh, C. Sohler, and D. P. Woodruff · 2010
Cited alongside, same era.
Online learning for matrix factorization and sparse coding
J. Mairal, F. Bach, J. Ponce, and G. Sapiro · 2010
Cited alongside, same era.
Hilbert space embeddings and metrics on probability measures
B. K. Sriperumbudur, A. Gretton, K. Fukumizu, B. Schölkopf, and G. R. G. Lanckriet · 2010
Cited alongside, same era.
Dimensionality reduction with subgaussian matrices: a unified theory
S. Dirksen · 2016
Later among the works it cites.
Streaming kernel principal component analysis
M. Ghashami, D. Perry, and J. M. Phillips · 2016
Later among the works it cites.
Deep neural networks with random Gaussian weights – a universal classification strategy?
R. Giryes, G. Sapiro, and A. M. Bronstein · 2016
Later among the works it cites.
Clustering data streams
S. Guha and N. Mishra · 2016
Later among the works it cites.
Stable low-rank matrix recovery via null space properties
M. Kabanava, R. Kueng, H. Rauhut, and U. Terstiege · 2016
Later among the works it cites.
On the equivalence between kernel quadrature rules and random feature expansions
F. Bach · 2017
Closest in time.
Towards understanding the invertibility of convolutional neural networks
A. C. Gilbert, Y. Zhang, K. Lee, Y. Zhang, and H. Lee · 2017
Closest in time.
Training Gaussian Mixture Models at Scale via Coresets
M. Lucic, M. Faulkner, A. K. 0001, and D. Feldman · 2017
Closest in time.
Recipes for stable linear embeddings from Hilbert spaces to ℝ m {\mathbb{R}}^{m}
G. Puy, M. E. Davies, and R. Gribonval · 2017
Closest in time.
Opening the black box of deep neural networks via information
R. Shwartz-Ziv and N. Tishby · 2017
Closest in time.
Demystifying MMD gans
M. Binkowski, D. J. Sutherland, M. Arbel, and A. Gretton · 2018
Closest in time.
Entropy and mutual information in models of deep neural networks
M. Gabrié, A. Manoel, C. Luneau, J. Barbier, N. Macris, F. Krzakala, and L. Zdeborová · 2018
Closest in time.
Neural tangent kernel: convergence and generalization in neural networks
A. Jacot, F. Gabriel, and C. Hongler · 2018
Closest in time.
Sketching for Large-Scale Learning of Mixture Models
N. Keriven, A. Bourrier, R. Gribonval, and P. Pérez · 2018
Closest in time.
Streaming kernel PCA with O ~ ( n ) \tilde{O}(\sqrt{n}) random features
E. Ullah, P. Mianjy, T. V. Marinov, and R. Arora · 2018
Closest in time.
On the Inductive Bias of Neural Tangent Kernels
A. Bietti and J. Mairal · 2019
Closest in time.
Differentially private compressive k k -means
V. Schellekens, A. Chatalic, F. Houssiau, Y.-A. De Montjoye, L. Jacques, and R. Gribonval · 2019
Closest in time.
Statistical learning guarantees for compressive clustering and compressive mixture modeling
R. Gribonval, G. Blanchard, N. Keriven, and Y. Traonmilin · 2020
Closest in time.
Nonasymptotic upper bounds for the reconstruction error of PCA
M. Reiß and M. Wahl · 2020
Closest in time.
Approximate kernel PCA using random features: Computational vs. statistical trade-off
B. Sriperumbudur and N. Sterge · 2020
Closest in time.
Gain with no pain: Efficiency of kernel-PCA by Nyström sampling
N. Sterge, B. Sriperumbudur, L. Rosasco, and A. Rudi · 2020
Closest in time.
Compressive Learning with Privacy Guarantees
A. Chatalic, V. Schellekens, F. Houssiau, Y.-A. De Montjoye, L. Jacques, and R. Gribonval · 2021
Closest in time.