Deterministic optimization does not consider uncertainties. This may lead to designs which are not robust or reliable. The use of safety factors is the common approach to cope with this problem. The main weaknesses of the achieved results are overdesign (too expensive) or underdesign (unreliable) because safety factors do not necessarily consider the special problem. Therefore robust design opt...

This work investigates a combined stochastic and deterministic optimization approach for multivariate mixture density estimation. Mixture probability density models are selected and optimized by combining the optimization characteristics of a multiagent stochastic optimization algorithm based on evolutionary programming and the expectation-maximization algorithm. Unlike the traditional finite m...

The development of simulation techniques that can elucidate the function of biomolecular nanodevices is still in its infancy. In this paper we summarize our approach to the investigation of structural properties of biomolecular systems with stochastic optimization methods. We briefly review the stochastic tunnelling method and summarize applications in two important areas of biomolecular struct...

We consider the problem of multi-class classification and a stochastic optimization approach to it. We derive risk bounds for stochastic mirror descent algorithm and provide examples of set geometries that make the use of the algorithm efficient in terms of error in k.

Optimal control problems involve the difficult task of determining time-varying profiles through dynamic optimization. Such problems become even more complex in practical situations where handling time dependent uncertainties becomes an important issue. Approaches to stochastic optimal control problems have been reported in the finance literature and are based on real option theory, combining I...

Stochastic optimization methods such as evolutionary algorithms and Markov Chain Monte Carlo methods usually involve a Markov search of the optimization domain. Evolutionary annealing is an evolutionary algorithm that leverages all the information gathered by previous queries to the cost function. Evolutionary annealing can be viewed either as simulated annealing with improved sampling or as a ...

Real world systems often have parameterized controllers which can be tuned to improve performance. Bayesian optimization methods provide for efficient optimization of these controllers, so as to reduce the number of required experiments on the expensive physical system. In this paper we address Bayesian optimization in the setting where performance is only observed through a stochastic binary o...

Simulation plays a vital role in analyzing DEDS. However, using simulation to analyze complex systems can he time-consuming and expensive. Particularly, in the case of precise performance evaluation, computing budget, time constraint, and pseudo-random number generator limitations can become prohibitive. Ordinal optimization is an effective approach for improving the efficiency of simulation an...

This paper proposes a stochastic framework for demand response (DR) aggregator to procure DR from customers and sell it to purchasers in the wholesale electricity market. The aggregator assigns fixed DR contracts with customers based on three different load reduction strategies. In the presented problem the uncertainty of market price is considered and the risk of aggregator participation is ma...