Corpus ID: 211252751

Debiasing Stochastic Gradient Descent to handle missing values

@article{Sportisse2020DebiasingSG,
  title={Debiasing Stochastic Gradient Descent to handle missing values},
  author={Aude Sportisse and Claire Boyer and Aymeric Dieuleveut and Julie Josse},
  journal={arXiv: Statistics Theory},
  year={2020}
}
  • Aude Sportisse, Claire Boyer, +1 author Julie Josse
  • Published 2020
  • Mathematics
  • arXiv: Statistics Theory
  • A major caveat of large scale data is their incom-pleteness. We propose an averaged stochastic gradient algorithm handling missing values in linear models. This approach has the merit to be free from the need of any data distribution modeling and to account for heterogeneous missing proportion. In both streaming and finite-sample settings, we prove that this algorithm achieves convergence rate of O(1 n) at the iteration n, the same as without missing values. We show the convergence behavior and… CONTINUE READING

    Figures and Tables from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 26 REFERENCES

    Adapted Stochastic Gradient Descent for Linear Systems with Missing Data

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n)

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL