Summary
Main objects here are stochastic programs, possibly non-convex. We develop an algorithm that combines gradient projection with the heavy-ball method. What emerges is a constrained, stochastic, second-order process. Some friction feeds into and stabilizes myopic approximations. Convergence obtains under weak and natural conditions, an important one being that accumulated marginal payoff remains bounded above.
Thanks for support are due Ruhrgas, Røwdes fond and Norges Bank.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
F. Alvarez, On the minimizing property of a second order dissipative system in Hilbert spaces, SIAM J. Control Opt. 38,4, 1102–1119 (2000).
F. Alvarez and J. M. Pérez, A dynamical system associated with Newton’s method for parametric approximations of convex minimization problem, Appl. Math. Optm. 38, 193–217 (1998).
H. Attouch, X. Goudou, and P. Redont, The heavy ball with friction method I, The continuous dynamical system: Global exploration of the local minima of a real-valued function by asymptotic analysis of a dissipative dynamical system, Communications in Contemporary Mathematics 2,1, 1–34 (2000).
H. Attouch and P. Redont, The second-order in time continuous Newton method, in M. Lassonde, Approximation, Optimization and Mathematical Economic, Physica-Verlag, Heidelberg 4–36 (2001).
J. P. Aubin and A. Cellina, Differential Inclusions, Springer-Verlag, Berlin (1984).
M. Benaim, A dynamical system approach to stochastic approximation, SIAM J. of Control and Optimization 34, 437–472 (1996).
M. Benaim and M. W. Hirsch, Mixed equilibria and dynamical systems arising from fictitious play in perturbed games, Games and Economic Behavior 29, 36–72 (1999).
D. P. Bertsekas, Nonlinear Programming, Athena Scientific, Mass. (1995).
H. Brézis, Operateur maximaux monotones, Mathematics Studies 5, North Holland (1973).
Y. M. Ermoliev and R. J.-B. Wets (Eds.) Numerical Techniques for Stochastic Optimization, Springer-Verlag, Berlin (1988).
S. D. Flam and J. Morgan, Newtonian mechanics and Nash play, manuscript (2001).
J.-B. Hiriart-Urruty and C. Lemaréchal, Convex Analysis and Minimization Algorithms, Springer-Verlag, Berlin (1993).
B. T. Polyak, Some methods of speeding up the convergence of iteration methods, Z. VyCisl. Math. i Fiz. 4, 1–17 (1964)..
R. T. Rockafellar, Convex Analysis, Princeton University Press (1970).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Flåm, S.D. (2004). Optimization under Uncertainty using Momentum. In: Marti, K., Ermoliev, Y., Pflug, G. (eds) Dynamic Stochastic Optimization. Lecture Notes in Economics and Mathematical Systems, vol 532. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-55884-9_12
Download citation
DOI: https://doi.org/10.1007/978-3-642-55884-9_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40506-1
Online ISBN: 978-3-642-55884-9
eBook Packages: Springer Book Archive