On the dynamics of gradient descent for autoencoders

Thanh V. Nguyen, Raymond K.W. Wong, Chinmay Hegde

    Research output: Contribution to conferencePaperpeer-review

    Abstract

    We provide a series of results for unsupervised learning with autoencoders. Specifically, we study shallow two-layer autoencoder architectures with shared weights. We focus on three generative models for data that are common in statistical machine learning: (i) the mixture-of-gaussians model, (ii) the sparse coding model, and (iii) the sparsity model with non-negative coefficients. For each of these models, we prove that under suitable choices of hyperparameters, architectures, and initialization, autoencoders learned by gradient descent can successfully recover the parameters of the corresponding model. To our knowledge, this is the first result that rigorously studies the dynamics of gradient descent for weight-sharing autoencoders. Our analysis can be viewed as theoretical evidence that shallow autoencoder modules indeed can be used as feature learning mechanisms for a variety of data models, and may shed insight on how to train larger stacked architectures with autoencoders as basic building blocks.

    Original languageEnglish (US)
    StatePublished - 2020
    Event22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019 - Naha, Japan
    Duration: Apr 16 2019Apr 18 2019

    Conference

    Conference22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019
    CountryJapan
    CityNaha
    Period4/16/194/18/19

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Statistics and Probability

    Fingerprint Dive into the research topics of 'On the dynamics of gradient descent for autoencoders'. Together they form a unique fingerprint.

    Cite this