S. Bhatnagar and V. S. Borkar. Multiscale stochastic approximation for parametric optimization of hidden Markov models. Prob. Engg. and Info. Sci., 11:509--522, 1997.  Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
A Simulation-Based Algorithm for Ergodic Control of.. - Bhatnagar, Borkar, al. (2006) Self-citation (Bhatnagar Borkar) (Correct)
No context found.
S. Bhatnagar and V. S. Borkar. Multiscale stochastic approximation for parametric optimization of hidden Markov models. Prob. Engg. and Info. Sci., 11:509--522, 1997.
Randomized Difference Two-Timescale Simultaneous.. - Bhatnagar, Fu, al. (2000) (1 citation) Self-citation (Bhatnagar) (Correct)
....analysis [19] In [23] and [24] various stochastic approximation algorithms governed by finite di#erence estimates (as well as direct gradient estimates) were considered for optimizing a steady state performance measure with respect to a scalar parameter in a single server queue. In [3] [4] and [5] a more general setting for vector parameters and long run average performance measures is considered, in which the parameter is updated at deterministic instants that are obtained using two timescales; a faster timescale at which the system evolves, and a slower timescale at which the ....
....vector parameters and long run average performance measures is considered, in which the parameter is updated at deterministic instants that are obtained using two timescales; a faster timescale at which the system evolves, and a slower timescale at which the parameter is updated. Specifically, in [4], the parameter is updated at deterministically increasing time instants that are in turn obtained using two timescales (see also [2] On the other hand, in [5] the parameter is updated at every instant using coupled iterations that are governed by di#erent timescales. However as with any other ....
[Article contains additional citation context not shown here]
S. Bhatnagar and V. S. Borkar. Multiscale stochastic approximation for parametric optimization of hidden Markov models. Probability in the Engineering and Informational Sciences, 11:509--522, 1997.
Rate Based ABR Flow Control using Two Timescale SPSA - Bhatnagar, Fu, Marcus Self-citation (Bhatnagar) (Correct)
No context found.
S. Bhatnagar and V. S. Borkar. Multiscale stochastic approximation for parametric optimization of hidden Markov models. Probability in the Engineering and Informational Sciences, 11:509--522, 1997.
Optimal Multilevel Feedback Policies for ABR Flow Control.. - Bhatnagar, Fu, al. (1999) (1 citation) Self-citation (Bhatnagar) (Correct)
....mean queue length from a given fixed constant N 0 [34] 18] 30] In this paper, we consider parametrized policies that have several levels of control. We develop a simultaneous perturbation stochastic approximation (SPSA) 33] variant of a two timescale stochastic approximation algorithm [6] to obtain the optimal policy with this structure (see also [15] for application of SPSA to optimization of discrete event systems) The two timescale stochastic approximation algorithm developed in [6] for simulation based parametric optimization had the advantage that it updates the parameter at ....
.... approximation (SPSA) 33] variant of a two timescale stochastic approximation algorithm [6] to obtain the optimal policy with this structure (see also [15] for application of SPSA to optimization of discrete event systems) The two timescale stochastic approximation algorithm developed in [6] for simulation based parametric optimization had the advantage that it updates the parameter at increasing deterministic instants [2] without the need for regeneration as in [11] 13] This it achieves using di#erent timescales (or step size schedules) On the other hand, like other finite ....
[Article contains additional citation context not shown here]
S. Bhatnagar and V. S. Borkar. Multiscale stochastic approximation for parametric optimization of hidden Markov models. Probability in the Engineering and Informational Sciences, 11:509--522, 1997.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC