000186023 001__ 186023
000186023 005__ 20180317093351.0
000186023 037__ $$aCONF
000186023 245__ $$aAdaptive Coordinate Descent
000186023 269__ $$a2011
000186023 260__ $$c2011
000186023 336__ $$aConference Papers
000186023 520__ $$aIndependence from the coordinate system is one source of efficiency and robustness for the Covariance Matrix Adaptation Evolution Strategy (CMA-ES). The recently proposed Adaptive Encoding (AE) procedure generalizes CMA-ES adaptive mechanism, and can be used together with any optimization algorithm. Adaptive Encoding gradually builds a transformation of the coordinate system such that the new coordinates are as decorrelated as possible with respect to the objective function. But any optimization algorithm can then be used together with Adaptive Encoding, and this paper proposes to use one of the simplest of all, that uses a dichotomy procedure on each coordinate in turn. The resulting algorithm, termed Adaptive Coordinate Descent (ACiD), is analyzed on the Sphere function, and experimentally validated on BBOB testbench where it is shown to outperform the standard (1 + 1)-CMA-ES, and is found comparable to other state-of-the-art CMA-ES variants.
000186023 700__ $$0247037$$aLoshchilov, Ilya$$g230183
000186023 700__ $$aSchoenauer, Marc
000186023 700__ $$aSebag, Michele
000186023 7112_ $$aGenetic and Evolutionary Computation Conference (GECCO 2011)
000186023 773__ $$q885-892$$tGenetic and Evolutionary Computation Conference (GECCO 2011)
000186023 8564_ $$s847557$$uhttps://infoscience.epfl.ch/record/186023/files/GECCO2011_AdaptiveCoordinateDescent.pdf$$yn/a$$zn/a
000186023 909CO $$ooai:infoscience.tind.io:186023$$pSTI$$pconf
000186023 909C0 $$0252447$$pIMT$$xU10343
000186023 917Z8 $$x230183
000186023 917Z8 $$x148230
000186023 937__ $$aEPFL-CONF-186023
000186023 973__ $$aOTHER$$rREVIEWED$$sPUBLISHED
000186023 980__ $$aCONF