Stochastic approximation algorithms: Overview and recent trends

Bharath, B. N.; Borkar, Vivek S.

doi:10.1007/bf02823149

Cited by 31 publications

(24 citation statements)

References 103 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Its major complexity is in obtaining the estimates of partial derivatives of throughputs at each sensor. Stochastic algorithms are constrained by the "bias-variance dilemma" ( [29]), therefore, their convergence properties can be improved by careful selection of the parameters. In our examples, the starting points were chosen arbitrarily.…”

Section: Resultsmentioning

confidence: 99%

Distributed optimal self-organisation in a class of wireless sensor networks

Karnik

Kumar

Ieee Infocom 2004

View full text Add to dashboard Cite

Abstract-The work in this paper is motivated by the idea of using randomly deployed, ad hoc wireless networks of miniature smart sensors to serve as distributed instrumentation. We argue that in such applications it is important for the sensors to self-organise in a way that optimizes network throughput. We then identify and discuss two main problems of optimal selforganisation: (i) building an optimal topology, and (ii) tuning network access parameters such as the transmission attempt rate. We consider a simple random access model for sensor networks and formulate these problems as optimisation problems. We then present centralized as well as distributed algorithms for solving them. Results show that the performance improvement is substantial and implementation of such optimal self-organisation techniques may be worth the additional complexity.

show abstract

Section: Resultsmentioning

confidence: 99%

Distributed optimal self-organisation in a class of wireless sensor networks

Karnik

Kumar

Ieee Infocom 2004

View full text Add to dashboard Cite

show abstract

“…It is possible to apply a stochastic approximation [20] with convolution smoothing to the SEPNLS method in order to reach the global optimum [21]. The estimate of the time delay in GSNLS can be obtained by disturbing the time delay using a random value β:…”

Section: Sepnls and Gsnls Estimation Methodsmentioning

confidence: 99%

Continuous Ant Colony Optimization for Identification of Time Delays in the Linear Plant

Papliński

2012

Swarm and Evolutionary Computation

View full text Add to dashboard Cite

Abstract. Interpolated Ant Colony Optimization (IACO) for a continuous domain was proposed in the paper. The IACO uses the same mechanisms as the classical ACO applied to discrete optimization. The continuous search space is sampled by individuals on the basis of the linear interpolated trace of the pheromone. It allows to obtain a simple and efficient optimization algorithm. The proposed algorithm is then used to identify delays in linear dynamic systems. The examination results show that it is an effective tool for global optimization problems.

show abstract

“…Many of the neural network training algorithms, such as the simultaneous perturbation stochastic approximation algorithm (Spall, 1992), the Widrow Hoff algorithm (also known as the "least mean square" algorithm) (Haykin, 1999, pp.128-135), the Alopex algorithm (Harth & Tzanakou, 1974) and self-organizing maps (Kohonen, 1990), can be regarded as special instances of stochastic approximation. Refer to Bharath & Borkar (1999) for more discussions on this issue. Recently, stochastic approximation has been used with Markov chain Monte Carlo for solving maximum likelihood estimation problems (Gu & Kong, 1998;Delyon et al, 1999).…”

Section: Wwwintechopencommentioning

confidence: 99%

Annealing Stochastic Approximation Monte Carlo for Global Optimization

Liang¹

2008

Simulated Annealing

View full text Add to dashboard Cite

Stochastic approximation algorithms: Overview and recent trends

Cited by 31 publications

References 103 publications

Distributed optimal self-organisation in a class of wireless sensor networks

Distributed optimal self-organisation in a class of wireless sensor networks

Continuous Ant Colony Optimization for Identification of Time Delays in the Linear Plant

Annealing Stochastic Approximation Monte Carlo for Global Optimization

Contact Info

Product

Resources

About