Implicit Rank-Minimizing Autoencoder

An important component of autoencoders is the method by which the information capacity of the latent representation is minimized or limited. In this work, the rank of the covariance matrix of the codes is implicitly minimized by relying on the fact that gradient descent learning in multi-layer linear networks leads to minimum-rank solutions. By inserting a number of extra linear layers between the encoder and the decoder, the system spontaneously learns representations with a low effective dimension. The model, dubbed Implicit Rank-Minimizing Autoencoder (IRMAE), is simple, deterministic, and learns compact latent spaces. We demonstrate the validity of the method on several image generation and representation learning tasks.

[1]  Surya Ganguli,et al.  A mathematical theory of semantic development in deep neural networks , 2018, Proceedings of the National Academy of Sciences.

[2]  Sepp Hochreiter,et al.  GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium , 2017, NIPS.

[3]  Nathan Srebro,et al.  The Implicit Bias of Gradient Descent on Separable Data , 2017, J. Mach. Learn. Res..

[4]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[5]  Francis Bach,et al.  Implicit Regularization of Discrete Gradient Dynamics in Deep Linear Neural Networks , 2019, NeurIPS.

[6]  Kaiming He,et al.  Momentum Contrast for Unsupervised Visual Representation Learning , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Bernhard Schölkopf,et al.  From Variational to Deterministic Autoencoders , 2019, ICLR.

[8]  Michael S. Lewicki,et al.  Sparse Coding of Natural Images Using an Overcomplete Set of Limited Capacity Units , 2004, NIPS.

[9]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[10]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[11]  Oriol Vinyals,et al.  Neural Discrete Representation Learning , 2017, NIPS.

[12]  Christopher Burgess,et al.  beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework , 2016, ICLR 2016.

[13]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[14]  Yann LeCun,et al.  Saturating Auto-Encoders , 2013, ICLR 2013.

[15]  Sanjeev Arora,et al.  Implicit Regularization in Deep Matrix Factorization , 2019, NeurIPS.

[16]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[17]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Laurens van der Maaten,et al.  Self-Supervised Learning of Pretext-Invariant Representations , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Pascal Vincent,et al.  Contractive Auto-Encoders: Explicit Invariance During Feature Extraction , 2011, ICML.

[20]  Nathan Srebro,et al.  Implicit Regularization in Matrix Factorization , 2017, 2018 Information Theory and Applications Workshop (ITA).

[21]  Nathan Srebro,et al.  Implicit Bias of Gradient Descent on Linear Convolutional Networks , 2018, NeurIPS.

[22]  Geoffrey E. Hinton,et al.  A Simple Framework for Contrastive Learning of Visual Representations , 2020, ICML.

[23]  Marc'Aurelio Ranzato,et al.  Sparse Feature Learning for Deep Belief Networks , 2007, NIPS.

[24]  Nadav Cohen,et al.  Implicit Regularization in Deep Learning May Not Be Explainable by Norms , 2020, NeurIPS.

[25]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[26]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .