Asymptotic bias of stochastic gradient search

@article{Tadic2011AsymptoticBO,
  title={Asymptotic bias of stochastic gradient search},
  author={Vladislav B. Tadic and Arnaud Doucet},
  journal={IEEE Conference on Decision and Control and European Control Conference},
  year={2011},
  pages={722-727}
}
The asymptotic behavior of the stochastic gradient algorithm with a biased gradient estimator is analyzed. Relying on arguments based on differential geometry (Yomdin theorem and Lojasiewicz inequality), relatively tight bounds on the asymptotic bias of the iterates generated by such an algorithm are derived. The obtained results hold under mild and verifiable conditions and cover a broad class of complex stochastic gradient algorithms. Using these results, the asymptotic properties of the… CONTINUE READING

From This Paper

Topics from this paper.
5 Citations
30 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 30 references

Stochastic Approximation and Recursive Algorithms and Applications

  • H. J. Kushner, G. G. Yin
  • 2nd edition, Springer-Verlag
  • 2003
Highly Influential
3 Excerpts

Stochastic Approximation and Its Application

  • H.-F. Chen
  • Kluwer
  • 2002
Highly Influential
4 Excerpts

Markov Chains and Stochastic Stability

  • S. P. Meyn, R. L. Tweedie
  • 2nd Edition, Cambridge University Press
  • 2009

Stochastic Approximation: A Dynamical Systems Viewpoint

  • V. S. Borkar
  • Cambridge University Press
  • 2009
2 Excerpts

Analyticity

  • V. B. Tadić
  • Convergence and Convergence Rate of Recursive…
  • 2008
1 Excerpt

Similar Papers

Loading similar papers…