2017

Stochastic Gradient Descent in Continuous Time: A Central Limit Theorem

Sirignano, Justin, Spiliopoulos, Konstantinos

Understand

Stochastic gradient descent in continuous time (SGDCT) provides a computationally efficient method for the statistical learning of continuous-time models, which are widely used in science, engineering, and finance.

  • The SGDCT algorithm follows a (noisy) descent direction along a continuous stream of data.
  • The parameter updates occur in continuous time and satisfy a stochastic differential equation.
  • This paper analyzes the asymptotic convergence rate of the SGDCT algorithm by proving a central limit theorem (CLT) for strongly convex objective functions and, under slightly stronger conditions, for non-convex objective functions as well.

Built on

  • D. J. Sakrison, A continuous Kiefer-Wolfowitz procedure for random processes, Ann. Math. Statist., Vol. 35, No. 2, (1964), pp. 590-599

    1964

    Earlier work this paper cites.

  • N. Ikeda and S. Watanabe, A comparison theorem for solutions of stochastic differential equations and its applications, Osaka J. Math. , Vol. 14, (1977), pp. 619-633

    1977

    Earlier work this paper cites.

  • I. Basawa and B. Rao, Asymptotic inference for stochastic processes, Stochastic Processes and their Applications , Vol.10, No. 3, (1980), pp. 221-254

    1980

    Earlier work this paper cites.

  • A. Benveniste, M. Metivier, and P. Priouret, Adaptive Algorithms and Stochastic Approximations. Springer-Verlag , 1990

    1990

    Earlier work this paper cites.

  • G. Yin, I. Gupta, On a continuous time stochastic approximation problem, Acta Applicandae Mathematica, Vol. 33, Issue 1, (1993), pp. 3–20

    Original

    1993

    Earlier work this paper cites.

  • A. Yu. Veretennikov, On polynomial mixing bounds for stochastic differential equations, Stochastic Processes and their Applications Vol. 70, Issue 1, (1997), pp. 115-127

    1997

    Earlier work this paper cites.

Similar

  • B. L. S. P. Rao, Statistical inference for diffusion type processes, Arnold, 1999

    1999

    Cited alongside, same era.

  • K. Doya, Reinforcement learning in continuous time and space. Neural computation, Vol. 12, No. 1, pp. 219-245, 2000

    2000

    Cited alongside, same era.

  • O. Elerian, S. Chib, and N. Shephard, Likelihood inference for discretely observed nonlinear diffusions, Econometrica

    2001

    Cited alongside, same era.

  • E. Pardoux and A.Yu. Veretennikov, On Poisson equation and diffusion approximation 1, Annals of Probability

    2001

    Cited alongside, same era.

  • E. Pardoux and A. Y. Veretennikov, On Poisson equation and diffusion approximation 2, The Annals of Probability, Vol. 31, No. 3, (2003), pp. 1166-1192

    2003

    Cited alongside, same era.

  • Y. Kutoyants, Statistical Inference for Ergodic Diffusion Processes. Springer , 2004

    2004

    Cited alongside, same era.

Then

  • C. Chicone, Ordinary differential equations with applications, second edition, Springer, New York, 2006

    2006

    Later among the works it cites.

  • J. P. N. Bishwal, Parameter estimation in stochastic differential equations, in: Lecture Notes in Mathematics, Vol. 1923, Springer Science & Business Media, 2008

    2008

    Later among the works it cites.

  • M. Raginsky and J. Bouvrie, Continuous-time stochastic mirror descent on a network: variance reduction, consensus, convergence, IEEE Conference on Decision and Control , 2012

    2012

    Later among the works it cites.

  • S. Surace and J. Pfister, Online Maximum Likelihood Estimation of the Parameters of Partially Observed Diffusion Processes. arXiv:1611.00170, 2016

    Original

    2016

    Later among the works it cites.

  • J. Sirignano and K. Spiliopoulos, Stochastic Gradient Descent in Continuous Time, SIAM Journal on Financial Mathematics , Vol. 8, Issue 1, (2017), pp. 933–961

    2017

    Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…