Fetching the paper…
Reading the bibliography…
Autoencoders are the simplest neural network for unsupervised learning, and thus an ideal framework for studying feature learning.
The generalised product moment distribution in samples from a normal multivariate population
Wishart, J · 1928
Earlier work this paper cites.
The approximation of one matrix by another of lower rank
Eckart, C. and Young, G · 1936
Earlier work this paper cites.
Distribution of eigenvalues for some sets of random matrices
Marchenko, V. and Pastur, L · 1967
Earlier work this paper cites.
Simplified neuron model as a principal component analyzer
Oja, E · 1982
Earlier work this paper cites.
Auto-association by multilayer perceptrons and singular value decomposition
Bourlard, H. and Kamp, Y · 1988
Earlier work this paper cites.
Neural networks and principal component analysis: Learning from examples without local minima
Baldi, P. and Hornik, K · 1989
Earlier work this paper cites.
Optimal unsupervised learning in a single-layer linear feedforward neural network
Sanger, T. D · 1989
Earlier work this paper cites.
On-line backpropagation in two-layered neural networks
Riegler, P. and Biehl, M · 1995
Earlier work this paper cites.
The dynamics of on-line principal component analysis
Biehl, M. and Schlösser, E · 1998
Earlier work this paper cites.
Optimization of on-line principal component analysis
Schlösser, E., Saad, D., and Biehl, M · 1999
Earlier work this paper cites.
Pattern recognition and machine learning
Bishop, C · 2006
Earlier work this paper cites.
Learning multiple layers of features from tiny images
Krizhevsky, A., Hinton, G., et al · 2009
Earlier work this paper cites.
On-line learning in neural networks , volume 17
Saad, D · 2009
Earlier work this paper cites.
Matrix analysis
Horn, R. A. and Johnson, C. R · 2012
Earlier work this paper cites.
Implicit Regularization in Matrix Factorization
Gunasekar, S., Woodworth, B., Bhojanapalli, S., Neyshabur, B., and Srebro, N · 2017
Cited alongside, same era.
Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms
Xiao, H., Rasul, K., and Vollgraf, R · 2017
Cited alongside, same era.
Neural tangent kernel: Convergence and generalization in neural networks
Jacot, A., Gabriel, F., and Hongler, C · 2018
Cited alongside, same era.
On the spectrum of random features maps of high dimensional data
Liao, Z. and Couillet, R · 2018
Cited alongside, same era.
On the implicit bias of dropout
Mianjy, P., Arora, R., and Vidal, R · 2018
Cited alongside, same era.
From principal subspaces to principal components with linear autoencoders
Data-dependence of plateau phenomenon in learning with neural network — statistical mechanical analysis
Yoshida, Y. and Okada, M · 2019
Later among the works it cites.
Regularized linear autoencoders recover the principal components, eventually
Bao, X., Lucas, J., Sachdeva, S., and Grosse, R. B · 2020
Later among the works it cites.
Modeling the influence of data structure on learning in neural networks: The hidden manifold model
Goldt, S., Mézard, M., Krzakala, F., and Zdeborová, L · 2020
Later among the works it cites.
Universality laws for high-dimensional learning with random features
Hu, H. and Lu, Y. M · 2020
Later among the works it cites.
Eliminating the invariance on the loss landscape of linear autoencoders
Oftadeh, R., Shen, J., Wang, Z., and Shell, D · 2020
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Plaut, E · 2018
Cited alongside, same era.
Learning dynamics of linear denoising autoencoders
Pretorius, A., Kroon, S., and Kamper, H · 2018
Cited alongside, same era.
On lazy training in differentiable programming
Chizat, L., Oyallon, E., and Bach, F · 2019
Cited alongside, same era.
Implicit regularization of discrete gradient dynamics in linear neural networks
Gidel, G., Bach, F., and Lacoste-Julien, S · 2019
Cited alongside, same era.
Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup
Goldt, S., Advani, M., Saxe, A., Krzakala, F., and Zdeborová, L · 2019
Cited alongside, same era.
Loss landscapes of regularized linear autoencoders
Kunin, D., Bloom, J., Goeva, A., and Seed, C · 2019
Cited alongside, same era.
On the dynamics of gradient descent for autoencoders
Nguyen, T. V., Wong, R. K., and Hegde, C · 2019
Cited alongside, same era.
A First Course in Random Matrix Theory: For Physicists, Engineers and Data Scientists
Potters, M. and Bouchaud, J.-P · 2020
Later among the works it cites.
Learning curves of generic features maps for realistic datasets with a teacher-student model
Loureiro, B., Gerbelot, C., Cui, H., Goldt, S., Krzakala, F., Mézard, M., and Zdeborová, L · 2021
Later among the works it cites.
The generalization error of random features regression: Precise asymptotics and the double descent curve
Mei, S. and Montanari, A · 2021
Later among the works it cites.
The bootstrap framework: Generalization through the lens of online optimization
Nakkiran, P., Neyshabur, B., and Sedghi, H · 2021
Later among the works it cites.
Analysis of feature learning in weight-tied autoencoders via the mean field lens
Nguyen, P.-M · 2021
Later among the works it cites.
Classifying high-dimensional gaussian mixtures: Where kernel methods fail and neural networks succeed
Refinetti, M., Goldt, S., Krzakala, F., and Zdeborova, L · 2021
Later among the works it cites.
The gaussian equivalence of generative models for learning with shallow neural networks
Goldt, S., Loureiro, B., Reeves, G., Krzakala, F., Mezard, M., and Zdeborova, L · 2022
Closest in time.
Phase diagram of stochastic gradient descent in high-dimensional two-layer neural networks
Veiga, R., Stephan, L., Loureiro, B., Krzakala, F., and Zdeborová, L · 2022
Closest in time.