On Optimal Estimation Methods Using Stochastic Approximation Procedures
نویسندگان
چکیده
منابع مشابه
Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization, II: Shrinking Procedures and Optimal Algorithms
In this paper we study new stochastic approximation (SA) type algorithms, namely, the accelerated SA (AC-SA), for solving strongly convex stochastic composite optimization (SCO) problems. Specifically, by introducing a domain shrinking procedure, we significantly improve the large-deviation results associated with the convergence rate of a nearly optimal AC-SA algorithm presented in [4]. Moreov...
متن کاملRegression density estimation with variational methods and stochastic approximation
David J. Nott, Siew Li Tan, Mattias Villani and Robert Kohn, Regression density estimation with variational methods and stochastic approximation, 2012, Journal of Computational And Graphical Statistics, (21), 3, 797-820. Journal of Computational And Graphical Statistics is available online at informaworld TM : http://dx.doi.org/10.1080/10618600.2012.679897 Copyright: American Statistical Associ...
متن کاملOn Stochastic Approximation Methods in Reliability
Depending on the state of the stand-by equipment, can be distinguished loaded, non-loaded and partially loaded relief. In the case of loaded relief, the stand-by unit is in the same state as the operating unit and for this reason has the same intensity of breakdowns. In the partially loaded case, the stand-by device is loaded, but not so fully as the main equipment and for this reason has a dif...
متن کاملOn the convergence of linear stochastic approximation procedures
Many stochastic approximation procedures result in a stochastic algorithm of the form 1 hk+l = h k + (bk A k h k ) , k for all IC = 1 , 2 , 3 . . . . . Here, { b k , IC = 1,2 ,3 , . . .} is a Rd-valued process, { Ak , IC = 1 , 2 . 3 . . . . } is a symmetric, positive semidefinite Redxd-valued process, and { h k k = 1,2 ,3 , . .} is a sequence of stochastic estimates which hopefully converges to...
متن کاملUsing Stochastic Approximation Methods to Compute Optimal Base-Stock Levels in Inventory Control Problems
In this paper, we consider numerous inventory control problems for which the base-stock policies are known to be optimal and we propose stochastic approximation methods to compute the optimal base-stock levels. The existing stochastic approximation methods in the literature guarantee that their iterates converge, but not necessarily to the optimal base-stock levels. In contrast, we prove that t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The Annals of Statistics
سال: 1973
ISSN: 0090-5364
DOI: 10.1214/aos/1176342565