Papers
Topics
Authors
Recent
Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses.
Gemini 2.5 Flash
Gemini 2.5 Flash 80 tok/s
Gemini 2.5 Pro 60 tok/s Pro
GPT-5 Medium 23 tok/s Pro
GPT-5 High 26 tok/s Pro
GPT-4o 87 tok/s Pro
Kimi K2 173 tok/s Pro
GPT OSS 120B 433 tok/s Pro
Claude Sonnet 4 36 tok/s Pro
2000 character limit reached

A closed-measure approach to stochastic approximation (2112.05482v3)

Published 10 Dec 2021 in math.OC, math.DS, and math.PR

Abstract: This paper introduces a new method to tackle the issue of the almost sure convergence of stochastic approximation algorithms defined from a differential inclusion. Under the assumption of slowly decaying step-sizes, we establish that the set of essential accumulation points of the iterates belongs to the Birkhoff center associated with the differential inclusion. Unlike previous works, our results do not rely on the notion of asymptotic pseudotrajectories introduced by Bena\"im--Hofbauer--Sorin, which is the predominant technique to address the convergence problem. They follow as a consequence of Young's superposition principle for closed measures. This perspective bridges the gap between Young's principle and the notion of invariant measure of set-valued dynamical systems introduced by Faure and Roth. Also, the proposed method allows to obtain sufficient conditions under which the velocities locally compensate around any essential accumulation point.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (26)
  1. Gradient flows in metric spaces and in the space of probability measures. Lectures in Mathematics ETH Zürich. Birkhäuser Verlag, Basel, second edition, 2008.
  2. J.-P. Aubin and A. Cellina. Differential inclusions, volume 264 of Grundlehren der Mathematischen Wissenschaften [Fundamental Principles of Mathematical Sciences]. Springer-Verlag, Berlin, 1984. Set-valued maps and viability theory.
  3. Stochastic optimization with momentum: convergence, fluctuations, and traps avoidance. Electronic Journal of Statistics, 15(2):3892–3947, 2021.
  4. M. Benaïm. Dynamics of stochastic approximation algorithms. In Séminaire de Probabilités, XXXIII, volume 1709 of Lecture Notes in Math., pages 1–68. Springer, Berlin, 1999.
  5. M. Benaïm and M. W. Hirsch. Asymptotic pseudotrajectories and chain recurrent flows, with applications. J. Dynam. Differential Equations, 8(1):141–176, 1996.
  6. Stochastic approximations and differential inclusions. SIAM J. Control Optim., 44(1):328–348 (electronic), 2005.
  7. Stochastic approximations and differential inclusions. II. Applications. Math. Oper. Res., 31(4):673–695, 2006.
  8. M. Benaïm and S. J. Schreiber. Ergodic properties of weak asymptotic pseudotrajectories for semiflows. J. Dynam. Differential Equations, 12(3):579–598, 2000.
  9. Patrick Bernard. Young measures, superposition and transport. Indiana Univ. Math. J., 57(1):247–275, 2008.
  10. Long term dynamics of the subgradient method for lipschitz path differentiable functions. arXiv preprint arXiv:2006.00098, 2020.
  11. Conservative set valued fields, automatic differentiation, stochastic gradient methods and deep learning. Mathematical Programming, pages 1–33, 2020.
  12. V. S. Borkar. Stochastic approximation. A dynamical systems viewpoint. Cambridge University Press, Cambridge; Hindustan Book Agency, New Delhi, 2008.
  13. C. Castaing and M. Valadier. Convex analysis and measurable multifunctions. Lecture Notes in Mathematics, Vol. 580. Springer-Verlag, Berlin-New York, 1977.
  14. D Charalambos and Border Aliprantis. Infinite Dimensional Analysis: A Hitchhiker’s Guide. Springer-Verlag Berlin and Heidelberg GmbH & Company KG, 2013.
  15. Marie Duflo. Algorithmes stochastiques. Springer, 1996.
  16. M. Faure and G. Roth. Stochastic approximations of set-valued dynamical systems: convergence with positive probability to an attractor. Math. Oper. Res., 35(3):624–640, 2010.
  17. M. Faure and G. Roth. Ergodic properties of weak asymptotic pseudotrajectories for set-valued dynamical systems. Stoch. Dyn., 13(1):1250011, 23, 2013.
  18. Stochastic heavy ball. Electronic Journal of Statistics, 12(1):461–529, 2018.
  19. Fictitious play, shapley polygons, and the replicator equation. Games and Economic Behavior, 11(2):279–303, 1995.
  20. Martingale limit theory and its application. Academic press, 2014.
  21. Josef Hofbauer. Deterministic evolutionary game dynamics. In Evolutionary Game Dynamics, volume 69, pages 61–79. American Mathematical Society Providence, RI, 2011.
  22. Best response dynamics for continuous zero–sum games. Discrete & Continuous Dynamical Systems-B, 6(1):215, 2006.
  23. Stochastic approximation and recursive algorithms and applications, volume 35 of Applications of Mathematics (New York). Springer-Verlag, New York, second edition, 2003. Stochastic Modelling and Applied Probability.
  24. L. Ljung. Analysis of recursive stochastic algorithms. IEEE transactions on automatic control, 22(4):551–575, 1977.
  25. W. Miller and E. Akin. Invariant measures for set-valued dynamical systems. Trans. Amer. Math. Soc., 351(3):1203–1225, 1999.
  26. H. Robbins and S. Monro. A stochastic approximation method. In Herbert Robbins Selected Papers, pages 102–109. Springer, 1985.
Citations (8)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up