On the efficiency of Gaussian adaptation

@article{Kjellstrm1991OnTE,
  title={On the efficiency of Gaussian adaptation},
  author={Gregor Kjellstr{\"o}m},
  journal={Journal of Optimization Theory and Applications},
  year={1991},
  volume={71},
  pages={589-597}
}
  • G. Kjellström
  • Published 1 November 1991
  • Mathematics, Computer Science
  • Journal of Optimization Theory and Applications
Gaussian Adaptation (GA) is a stochastic process that adapts a Gaussian distribution to a region or set of feasible points in parameter space. As a result of the adaptation, GA becomes a maximum dispersion process extending the sampling over the largest possible volume in parameter space while keeping the probability of finding feasible points at a suitable level. For such a process, a general measure of efficiency is defined and an efficiency theorem is proved. 

Gaussian Adaptation Revisited - An Entropic View on Covariance Matrix Adaptation

TLDR
Gaussian Adaptation is revisited, a black-box optimizer for discrete and continuous problems that has been developed in the late 1960’s and its theoretical foundations are described and some key features of this algorithm are analyzed.

Gaussian Adaptation as a unifying framework for continuous black-box optimization and adaptive Monte Carlo sampling

TLDR
Modifications are presented that turn GaA into both a robust continuous black-box optimizer and an adaptive Random Walk Monte Carlo sampler that is conceptually similar to the seminal Adaptive Proposal (AP) algorithm.

Exploring the common concepts of adaptive MCMC and Covariance Matrix Adaptation schemes

  • C. Müller
  • Computer Science
    Theory of Evolutionary Algorithms
  • 2010
TLDR
This extended abstract summarizes the common concepts in adaptive MCMC and co- variance matrix adaptation schemes and presents how both types of methods can be unified within the Gaussian Adaptation framework and proposes a unification of both fields as “grand challenge” for future research.

Hard Problems in Gene Sequence Analysis: Classical Approaches and Suitability of Genetic Algorithms

TLDR
This work aimed to show how genetic algorithms can be used to solve hard problems on gene sequence analysis.

State of Art in Genetic Algorithms for Agricultural Systems

TLDR
Studies on the development and use of genetic algorithms in solving hard problems in the field of agricultural systems were identified, analyzed and are presented here.

A genetic Algorithm-Based feature selection

TLDR
The main contributions of this article are the development of a GA-based feature selector using a novel fitness function (kNN-based classification error) which enabled the GA to obtain a combinatorial set of feature giving rise to optimal accuracy.

Parameter Estimation of the Burr Type XII Distribution with a Progressively Interval-Censored Scheme Using Genetic Algorithm

TLDR
An extensive Monte Carlo simulation was conducted to evaluate the estimation performance of the typical maximum likelihood estimation method (TMLEM) and GA, and results show that the GA is competitive with the TMLEM in terms of resulting in a smaller bias and MSE in parameter estimation.

What Is Autonomous Search

TLDR
A general definition and a taxonomy of search processes with respect to their computation characteristics are proposed and some computation rules between computation stages are used to formalize the solver modifications and adaptations.

Global parameter identification of stochastic reaction networks from single trajectories

TLDR
A novel combination of an adaptive Monte Carlo sampler, called Gaussian Adaptation (GaA), and efficient exact stochastic simulation algorithms (SSA) that allows parameter identification from single Stochastic trajectories are proposed.

Heuristic Artificial Intelligent Algorithm for Genetic Algorithm

TLDR
A genetic algorithm is a search technique used in computing to find exact or approximate solutions to optimization and search problems that use techniques inspired by evolutionary biology such as inheritance, mutation, selection, and crossover.

References

SHOWING 1-5 OF 5 REFERENCES

Discrete optimization of digital filters using Gaussian adaptation and quadratic function minimization

TLDR
A new strategy for discrete optimization of a function F(x) is presented and it is demonstrated that the new method is more capable of finding good solutions than methods presented so far.

Stochastic optimization in system design

TLDR
This paper presents a stochastic optimization process, suitable for optimizing functions of a certain measure over generalized regions in R^n, and examples of a wide range of different optimization problems are given.

Optimization by Simulated Annealing

TLDR
A detailed analogy with annealing in solids provides a framework for optimization of the properties of very large and complex systems.

On Measures of "Useful" Information

An Introduction to Statistical Communication Theory

This IEEE Classic Reissue provides at an advanced level, a uniquely fundamental exposition of the applications of Statistical Communication Theory to a vast spectrum of important physical problems.