Corpus ID: 26164706

Stochastic gradient descent methods for estimation with large data sets

@article{Tran2015StochasticGD,
  title={Stochastic gradient descent methods for estimation with large data sets},
  author={D. Tran and Panos Toulis and E. Airoldi},
  journal={arXiv: Computation},
  year={2015}
}
  • D. Tran, Panos Toulis, E. Airoldi
  • Published 2015
  • Mathematics
  • arXiv: Computation
  • We develop methods for parameter estimation in settings with large-scale data sets, where traditional methods are no longer tenable. Our methods rely on stochastic approximations, which are computationally efficient as they maintain one iterate as a parameter estimate, and successively update that iterate based on a single data point. When the update is based on a noisy gradient, the stochastic approximation is known as standard stochastic gradient descent, which has been fundamental in modern… CONTINUE READING
    9 Citations

    Figures and Tables from this paper.

    The Hierarchical Adaptive Forgetting Variational Filter
    • V. Moens
    • Computer Science, Mathematics
    • ICML
    • 2018
    • 1
    • PDF
    Fully Implicit Online Learning
    • 1
    • PDF
    Copula variational inference
    • 56
    • PDF
    Stochastic Gradient Methods for Principled Estimation with Large Datasets
    • 1
    • PDF
    Sub-linear convergence of a stochastic proximal iteration method in Hilbert space

    References

    SHOWING 1-10 OF 99 REFERENCES
    Implicit stochastic gradient descent
    • 10
    • PDF
    Towards Stability and Optimality in Stochastic Gradient Descent
    • 37
    • PDF
    Stability and optimality in stochastic gradient descent
    • 8
    • PDF
    Scalable estimation strategies based on stochastic approximations: classical results and new insights
    • 27
    • PDF
    On Iterative Hard Thresholding Methods for High-dimensional M-Estimation
    • 149
    • PDF
    Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n)
    • 256
    • PDF
    Statistical analysis of stochastic gradient methods for generalized linear models
    • 43
    • PDF