Fetching the paper…
Reading the bibliography…
We present an intriguing discovery related to Random Fourier Features: in Gaussian kernel approximation, replacing the random Gaussian matrix by a properly scaled random orthogonal matrix significantly decreases kernel approximation error.
Harmonic analysis and the theory of probability
S. Bochner · 1955
Earlier work this paper cites.
Unified matrix treatment of the fast walsh-hadamard transform
B. J. Fino and V. R. Algazi · 1976
Earlier work this paper cites.
Support-vector networks
C. Cortes and V. Vapnik · 1995
Earlier work this paper cites.
Similarity estimation techniques from rounding algorithms
M. S. Charikar · 2002
Earlier work this paper cites.
Approximate nearest neighbors and the fast Johnson-Lindenstrauss transform
N. Ailon and B. Chazelle · 2006
Earlier work this paper cites.
Training linear SVMs in linear time
T. Joachims · 2006
Earlier work this paper cites.
Lecture notes on Stein’s method and applications
S. Chatterjee · 2007
Earlier work this paper cites.
Random features for large-scale kernel machines
A. Rahimi and B. Recht · 2007
Earlier work this paper cites.
Max-margin additive classifiers for detection
S. Maji and A. C. Berg · 2009
Earlier work this paper cites.
Aspects of multivariate statistical theory
R. J. Muirhead · 2009
Earlier work this paper cites.
Random fourier approximations for skewed multiplicative histogram kernels
F. Li, C. Ionescu, and C. Sminchisescu · 2010
Cited alongside, same era.
Quasi-Monte Carlo Methods
H. Niederreiter · 2010
Cited alongside, same era.
Generalized RBF feature maps for efficient detection
V. Sreekanth, A. Vedaldi, A. Zisserman, and C. Jawahar · 2010
Cited alongside, same era.
Pegasos: Primal estimated sub-gradient solver for SVM, volume = 127, year = 2011
S. Shalev-Shwartz, Y. Singer, N. Srebro, and A. Cotter · 2011
Cited alongside, same era.
Random feature maps for dot product kernels
P. Kar and H. Karnick · 2012
Cited alongside, same era.
Efficient additive kernels via explicit feature maps
A. Vedaldi and A. Zisserman · 2012
Cited alongside, same era.
Practical and optimal lsh for angular distance
A. Andoni, P. Indyk, T. Laarhoven, I. Razenshteyn, and L. Schmidt · 2015
Later among the works it cites.
An exploration of parameter redundancy in deep networks with circulant projections
Y. Cheng, F. X. Yu, R. S. Feris, S. Kumar, A. Choudhary, and S.-F. Chang · 2015
Later among the works it cites.
Recycling randomness with structure for sublinear time kernel expansions
K. Choromanski and V. Sindhwani · 2015
Later among the works it cites.
Spherical random features for polynomial kernels
J. Pennington, F. X. Yu, and S. Kumar · 2015
Later among the works it cites.
Optimal rates for random fourier features
B. Sriperumbudur and Z. Szabó · 2015
Later among the works it cites.
Compact nonlinear maps and circulant extensions
F. X. Yu, S. Kumar, H. Rowley, and S.-F. Chang · 2015
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Nyström method vs random fourier features: A theoretical and empirical comparison
T. Yang, Y.-F. Li, M. Mahdavi, R. Jin, and Z.-H. Zhou · 2012
Cited alongside, same era.
Fastfood – approximating kernel expansions in loglinear time
Q. Le, T. Sarlós, and A. Smola · 2013
Cited alongside, same era.
Quasi-monte carlo feature maps for shift-invariant kernels
J. Yang, V. Sindhwani, H. Avron, and M. Mahoney · 2014
Cited alongside, same era.
Circulant binary embedding
F. X. Yu, S. Kumar, Y. Gong, and S.-F. Chang · 2014
Cited alongside, same era.
Later among the works it cites.
Fast orthogonal projection based on kronecker product
X. Zhang, F. X. Yu, R. Guo, S. Kumar, S. Wang, and S.-F. Chang · 2015
Later among the works it cites.
Triplespin-a generic compact paradigm for fast machine learning computations
K. Choromanski, F. Fagan, C. Gouy-Pailler, A. Morvan, T. Sarlos, and J. Atif · 2016
Closest in time.
Fast cross-polytope locality-sensitive hashing
C. Kennedy and R. Ward · 2016
Closest in time.
Generalization properties of learning with random features
A. Rudi, R. Camoriano, and L. Rosasco · 2016
Closest in time.