Corpus ID: 102350811

A Generalization Bound for Online Variational Inference

@inproceedings{ChriefAbdellatif2019AGB,
  title={A Generalization Bound for Online Variational Inference},
  author={Badr-Eddine Ch{\'e}rief-Abdellatif and Pierre Alquier and Mohammad Emtiyaz Khan},
  booktitle={ACML},
  year={2019}
}
  • Badr-Eddine Chérief-Abdellatif, Pierre Alquier, Mohammad Emtiyaz Khan
  • Published in ACML 2019
  • Computer Science, Mathematics
  • Bayesian inference provides an attractive online-learning framework to analyze sequential data, and offers generalization guarantees which hold even under model mismatch and with adversaries. Unfortunately, exact Bayesian inference is rarely feasible in practice and approximation methods are usually employed, but do such methods preserve the generalization properties of Bayesian inference? In this paper, we show that this is indeed the case for some variational inference (VI) algorithms. We… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-3 OF 3 CITATIONS

    Graph Convolutional Topic Model for Data Streams

    VIEW 2 EXCERPTS
    CITES METHODS & BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 55 REFERENCES

    Online Learning and Online Convex Optimization

    VIEW 12 EXCERPTS
    HIGHLY INFLUENTIAL

    A New Approach to Linear Filtering and Prediction Problems

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    Introduction to Online Convex Optimization

    • Elad Hazan
    • Mathematics, Computer Science
    • Foundations and Trends in Optimization
    • 2016
    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Introduction to Online Optimization

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Prediction, learning, and games

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Gaussian Kullback-Leibler approximate inference

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL