A Method for Handling Uncertainty in Evolutionary Optimization With an Application to Feedback Control of Combustion

By Nikolaus Hansen, Andreas Niederberger, Lino Guzzella, Petros Koumoutsakos. IEEE Transactions on Evolutionary Computation, 2009

311 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computational Theory and Mathematics, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/23a1a45cc670592084d4eadc358a8f1fbfc755f7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computational Theory and Mathematics

In Control and Systems Engineering

Citations in the corpus

The CMA Evolution Strategy: A Tutorial (2016, unknown): “A similar boundary handling with a component-wise adaptive α is described in [22].”
Machine Learning for Fluid Mechanics (2019, unknown): “Hansen et al. (2009) proposed an approach to enhance the capabilities of evolutionary algorithms for online optimization of a combustor test-rig.”
CMA-ES for Hyperparameter Optimization of Deep Neural Networks (2016, unknown): “We didn’t try to employ any noise reduction techniques (Hansen et al., 2009) or surrogate models (Loshchilov et al.”
Natural Evolution Strategies (2008, background): “, 2005; Klockgether and Schwefel, 1970) and control (Hansen et al., 2009).”
Markov Chain Analysis of Cumulative Step-Size Adaptation on a Linear Constrained Problem (2015, background): “(Hansen et al., 2009; Arnold and Porter, 2015) with adaptive penalty weights) or by the constraint value itself (e.”
A linear time natural evolution strategy for non-separable functions (2011, background): “1 2 u (u>u) 1 2 = 1 (u>u) 1 2 u u>u u>u u . The natural gradient on cand vis given by letting u/O~ulogp(xj), thanks to the invariance property: O~clogp(xj) = r 1O~ulogp(xj)>v (7) O~vlogp(xj) = r 1 h O~ulogp(xj) O~ulogp(xj) >v v i , (8) Note that computing O~clogp(xj) and O~vlog”
Well placement optimization with the covariance matrix adaptation evolution strategy and meta-models (2011, methodology): “2 The penalization method depends in general on other parameters which are on the other hand much less critical and which are tuned beforehand to be suitable for a wide range of problems [32].”
Black-box data-efficient policy search for robotics (2017, methodology): “[35] to improve the behavior of CMA-ES with noisy functions (called UH-CMA-ES).”
Data-driven discovery of Koopman eigenfunctions for control (2017, background): “A wide range of data-driven and nonlinear control approaches exist in the literature, including model-free adaptive control [12]–[14], extremum-seeking [15]–[17], gain scheduling [18], [19], feedback linearization [20]–[22], describing functions [23], sliding mode control [24]–[26], singular perturb”