Browse/search for people

Publication - Dr Vladislav Tadic

    Asymptotic bias of stochastic gradient search

    Citation

    Tadic, VB & Doucet, A, 2017, ‘Asymptotic bias of stochastic gradient search’. Annals of Applied Probability, vol 27., pp. 3255-3304

    Abstract

    The asymptotic behavior of the stochastic gradient algorithm using biased gradient estimates is analyzed. Relying on arguments based on dynamic system theory (chain-recurrence) and differential geometry (Yomdin theorem and Lojasiewicz inequalities), upper bounds on the asymptotic bias of this algorithm are derived. The results hold under mild conditions and cover a broad class of algorithms used in machine learning, signal processing and statistics.

    Full details in the University publications repository