The Experts below are selected from a list of 49833 Experts worldwide ranked by ideXlab platform
Bo Liu - One of the best experts on this subject based on the ideXlab platform.
-
a parallel Surrogate Model assisted evolutionary algorithm for electromagnetic design optimization
IEEE Transactions on Emerging Topics in Computational Intelligence, 2019Co-Authors: Mobayode O Akinsolu, Bo Liu, Vic Grout, Pavlos I Lazaridis, Maria Evelina Mognaschi, Paolo Di BarbaAbstract:Optimization efficiency is a major challenge for electromagnetic (EM) device, circuit, and machine design. Although both Surrogate Model-assisted evolutionary algorithms (SAEAs) and parallel computing are playing important roles in addressing this challenge, there is little research that investigates their integration to benefit from both techniques. In this paper, a new method, called parallel SAEA for electromagnetic design (PSAED), is proposed. A state-of-the-art SAEA framework, Surrogate Model-aware evolutionary search, is used as the foundation of PSAED. Considering the landscape characteristics of EM design problems, three differential evolution mutation operators are selected and organized in a particular way. A new SAEA framework is then proposed to make use of the selected mutation operators in a parallel computing environment. PSAED is tested by a micromirror and a dielectric resonator antenna as well as four mathematical benchmark problems of various complexity. Comparisons with state-of-the-art methods verify the advantages of PSAED in terms of efficiency and optimization capacity.
-
efficient global optimisation of microwave antennas based on a parallel Surrogate Model assisted evolutionary algorithm
Iet Microwaves Antennas & Propagation, 2019Co-Authors: Bo Liu, Mobayode O Akinsolu, N T Ali, Raed A AbdalhameedAbstract:Computational efficiency is a major challenge for evolutionary algorithm (EA)-based antenna optimisation methods due to the computationally expensive electromagnetic simulations. Surrogate Model-assisted EAs considerably improve the optimisation efficiency, but most of them are sequential methods, which cannot benefit from parallel simulation of multiple candidate designs for further speed improvement. To address this problem, a new method, called parallel Surrogate Model-assisted hybrid differential evolution for antenna optimisation (PSADEA), is proposed. The performance of PSADEA is demonstrated by a dielectric resonator antenna, a Yagi-Uda antenna, and three mathematical benchmark problems. Experimental results show high operational performance in a few hours using a normal desktop 4-core workstation. Comparisons show that PSADEA possesses significant advantages in efficiency compared to a state-of-the-art Surrogate Model-assisted EA for antenna optimisation, the standard parallel differential evolution algorithm, and parallel particle swarm optimisation. In addition, PSADEA also shows stronger optimisation ability compared to the above reference methods for challenging design cases.
-
global optimization of microwave filters based on a Surrogate Model assisted evolutionary algorithm
IEEE Transactions on Microwave Theory and Techniques, 2017Co-Authors: Bo Liu, Hao Yang, M J LancasterAbstract:Local optimization is a routine approach for full-wave optimization of microwave filters. For filter optimization problems with numerous local optima or where the initial design is not near to the optimal region, the success rate of the routine method may not be high. Traditional global optimization techniques have a high success rate for such problems, but are often prohibitively computationally expensive considering the cost of full-wave electromagnetic simulations. To address the above challenge, a new method, called Surrogate Model-assisted evolutionary algorithm for filter optimization (SMEAFO), is proposed. In SMEAFO, considering the characteristics of filter design landscapes, Gaussian process Surrogate Modeling, differential evolution operators, and Gaussian local search are organized in a particular way to balance the exploration ability and the Surrogate Model quality, so as to obtain high-quality results in an efficient manner. The performance of SMEAFO is demonstrated by two real-world design cases (a waveguide filter and a microstrip filter), which do not appear to be solvable by popular local optimization techniques. Experiments show that SMEAFO obtains high-quality designs comparable with global optimization techniques but within a reasonable amount of time. Moreover, SMEAFO is not restricted by certain types of filters or responses. The SMEAFO-based filter design optimization tool can be downloaded from http://fde.cadescenter.com .
-
a multi fidelity Surrogate Model assisted evolutionary algorithm for computationally expensive optimization problems
Journal of Computational Science, 2016Co-Authors: Bo Liu, Slawomir Koziel, Qingfu ZhangAbstract:Integrating data-driven Surrogate Models and simulation Models of different accuracies (or fidelities) in a single algorithm to address computationally expensive global optimization problems has recently attracted considerable attention. However, handling discrepancies between simulation Models with multiple fidelities in global optimization is a major challenge. To address it, the two major contributions of this paper include: (1) development of a new multi-fidelity Surrogate-Model-based optimization framework, which substantially improves reliability and efficiency of optimization compared to many existing methods, and (2) development of a data mining method to address the discrepancy between the low- and high-fidelity simulation Models. A new efficient global optimization method is then proposed, referred to as multi-fidelity Gaussian process and radial basis function-Model-assisted memetic differential evolution. Its advantages are verified by mathematical benchmark problems and a real-world antenna design automation problem.
-
a gaussian process Surrogate Model assisted evolutionary algorithm for medium scale expensive optimization problems
IEEE Transactions on Evolutionary Computation, 2014Co-Authors: Bo Liu, Qingfu Zhang, Georges GielenAbstract:Surrogate Model assisted evolutionary algorithms (SAEAs) have recently attracted much attention due to the growing need for computationally expensive optimization in many real-world applications. Most current SAEAs, however, focus on small-scale problems. SAEAs for medium-scale problems (i.e., 20-50 decision variables) have not yet been well studied. In this paper, a Gaussian process Surrogate Model assisted evolutionary algorithm for medium-scale computationally expensive optimization problems (GPEME) is proposed and investigated. Its major components are a Surrogate Model-aware search mechanism for expensive optimization problems when a high-quality Surrogate Model is difficult to build and dimension reduction techniques for tackling the “curse of dimensionality.” A new framework is developed and used in GPEME, which carefully coordinates the Surrogate Modeling and the evolutionary search, so that the search can focus on a small promising area and is supported by the constructed Surrogate Model. Sammon mapping is introduced to transform the decision variables from tens of dimensions to a few dimensions, in order to take advantage of Gaussian process Surrogate Modeling in a low-dimensional space. Empirical studies on benchmark problems with 20, 30, and 50 variables and a real-world power amplifier design automation problem with 17 variables show the high efficiency and effectiveness of GPEME. Compared to three state-of-the-art SAEAs, better or similar solutions can be obtained with 12% to 50% exact function evaluations.
Scott E Field - One of the best experts on this subject based on the ideXlab platform.
-
Surrogate Model for gravitational wave signals from comparable and large mass ratio black hole binaries
Physical Review D, 2020Co-Authors: Nur E M Rifat, Scott E Field, Gaurav Khanna, V VarmaAbstract:Gravitational wave signals from compact astrophysical sources such as those observed by LIGO and Virgo require a high-accuracy, theory-based waveform Model for the analysis of the recorded signal. Current inspiral-merger-ringdown Models are calibrated only up to moderate mass ratios, thereby limiting their applicability to signals from high-mass-ratio binary systems. We present EMRISur1dq1e4, a reduced-order Surrogate Model for gravitational waveforms of $13\text{ }500\text{ }\text{ }M$ in duration and including several harmonic modes for nonspinning black hole binary systems with mass ratios varying from 3 to 10000, thus vastly expanding the parameter range beyond the current Models. This Surrogate Model is trained on waveform data generated by point-particle black hole perturbation theory (ppBHPT) both for large-mass-ratio and comparable mass-ratio binaries. We observe that the gravitational waveforms generated through a simple application of ppBHPT to the comparable mass-ratio cases agree surprisingly well with those from full numerical relativity after a rescaling of the ppBHPT's total mass parameter. This observation and the EMRISur1dq1e4 Surrogate Model will enable data analysis studies in the high-mass-ratio regime, including potential intermediate-mass-ratio signals from LIGO/Virgo and extreme-mass-ratio events of interest to the future space-based observatory LISA.
-
Surrogate Model of hybridized numerical relativity binary black hole waveforms
Physical Review D, 2019Co-Authors: V Varma, Scott E Field, J Blackman, Mark A Scheel, Lawrence E Kidder, Harald P PfeifferAbstract:Numerical relativity (NR) simulations provide the most accurate binary black hole gravitational waveforms, but are prohibitively expensive for applications such as parameter estimation. Surrogate Models of NR waveforms have been shown to be both fast and accurate. However, NR-based Surrogate Models are limited by the training waveforms' length, which is typically about 20 orbits before merger. We remedy this by hybridizing the NR waveforms using both post-Newtonian and effective one-body waveforms for the early inspiral. We present NRHybSur3dq8, a Surrogate Model for hybridized nonprecessing numerical relativity waveforms, that is valid for the entire LIGO band (starting at 20 Hz) for stellar mass binaries with total masses as low as $2.25\text{ }\text{ }{M}_{\ensuremath{\bigodot}}$. We include the $\ensuremath{\ell}\ensuremath{\le}4$ and (5, 5) spin-weighted spherical harmonic modes but not the (4, 1) or (4, 0) modes. This Model has been trained against hybridized waveforms based on 104 NR waveforms with mass ratios $q\ensuremath{\le}8$, and $|{\ensuremath{\chi}}_{1z}|,|{\ensuremath{\chi}}_{2z}|\ensuremath{\le}0.8$, where ${\ensuremath{\chi}}_{1z}$ (${\ensuremath{\chi}}_{2z}$) is the spin of the heavier (lighter) black hole in the direction of orbital angular momentum. The Surrogate reproduces the hybrid waveforms accurately, with mismatches $\ensuremath{\lesssim}3\ifmmode\times\else\texttimes\fi{}{10}^{\ensuremath{-}4}$ over the mass range $2.25\text{ }\text{ }{M}_{\ensuremath{\bigodot}}\ensuremath{\le}M\ensuremath{\le}300\text{ }\text{ }{M}_{\ensuremath{\bigodot}}$. At high masses ($M\ensuremath{\gtrsim}40\text{ }\text{ }{M}_{\ensuremath{\bigodot}}$), where the merger and ringdown are more prominent, we show roughly 2 orders of magnitude improvement over existing waveform Models. We also show that the Surrogate works well even when extrapolated outside its training parameter space range, including at spins as large as 0.998. Finally, we show that this Model accurately reproduces the spheroidal-spherical mode mixing present in the NR ringdown signal.
-
numerical relativity waveform Surrogate Model for generically precessing binary black hole mergers
Physical Review D, 2017Co-Authors: J Blackman, Scott E Field, Mark A Scheel, Chad R Galley, Christian D Ott, Michael Boyle, Lawrence E Kidder, Harald P PfeifferAbstract:A generic, noneccentric binary black hole (BBH) system emits gravitational waves (GWs) that are completely described by seven intrinsic parameters: the black hole spin vectors and the ratio of their masses. Simulating a BBH coalescence by solving Einstein’s equations numerically is computationally expensive, requiring days to months of computing resources for a single set of parameter values. Since theoretical predictions of the GWs are often needed for many different source parameters, a fast and accurate Model is essential. We present the first Surrogate Model for GWs from the coalescence of BBHs including all seven dimensions of the intrinsic noneccentric parameter space. The Surrogate Model, which we call NRSur7dq2, is built from the results of 744 numerical relativity simulations. NRSur7dq2 covers spin magnitudes up to 0.8 and mass ratios up to 2, includes all l≤4 modes, begins about 20 orbits before merger, and can be evaluated in ∼50 ms. We find the largest NRSur7dq2 errors to be comparable to the largest errors in the numerical relativity simulations, and more than an order of magnitude smaller than the errors of other waveform Models. Our Model, and more broadly the methods developed here, will enable studies that were not previously possible when using highly accurate waveforms, such as parameter inference and tests of general relativity with GW observations.
-
a Surrogate Model of gravitational waveforms from numerical relativity simulations of precessing binary black hole mergers
Physical Review D, 2017Co-Authors: J Blackman, Scott E Field, Mark A Scheel, Chad R Galley, Daniel A Hemberger, P Schmidt, R J E SmithAbstract:We present the first Surrogate Model for gravitational waveforms from the coalescence of precessing binary black holes. We call this Surrogate Model NRSur4d2s. Our methodology significantly extends recently introduced reduced-order and Surrogate Modeling techniques, and is capable of directly Modeling numerical relativity waveforms without introducing phenomenological assumptions or approximations to general relativity. Motivated by GW150914, LIGO’s first detection of gravitational waves from merging black holes, the Model is built from a set of 276 numerical relativity (NR) simulations with mass ratios q ≤ 2, dimensionless spin magnitudes up to 0.8, and the restriction that the initial spin of the smaller black hole lies along the axis of orbital angular momentum. It produces waveforms which begin ∼ 30 gravitational wave cycles before merger and continue through ringdown, and which contain the effects of precession as well as all l∈{2,3} spin-weighted spherical-harmonic modes. We perform cross-validation studies to compare the Model to NR waveforms not used to build the Model and find a better agreement within the parameter range of the Model than other, state-of-the-art precessing waveform Models, with typical mismatches of 10^(-3). We also construct a frequency domain Surrogate Model (called NRSur4d2s_FDROM) which can be evaluated in 50 ms and is suitable for performing parameter estimation studies on gravitational wave detections similar to GW150914.
V Varma - One of the best experts on this subject based on the ideXlab platform.
-
Surrogate Model for gravitational wave signals from comparable and large mass ratio black hole binaries
Physical Review D, 2020Co-Authors: Nur E M Rifat, Scott E Field, Gaurav Khanna, V VarmaAbstract:Gravitational wave signals from compact astrophysical sources such as those observed by LIGO and Virgo require a high-accuracy, theory-based waveform Model for the analysis of the recorded signal. Current inspiral-merger-ringdown Models are calibrated only up to moderate mass ratios, thereby limiting their applicability to signals from high-mass-ratio binary systems. We present EMRISur1dq1e4, a reduced-order Surrogate Model for gravitational waveforms of $13\text{ }500\text{ }\text{ }M$ in duration and including several harmonic modes for nonspinning black hole binary systems with mass ratios varying from 3 to 10000, thus vastly expanding the parameter range beyond the current Models. This Surrogate Model is trained on waveform data generated by point-particle black hole perturbation theory (ppBHPT) both for large-mass-ratio and comparable mass-ratio binaries. We observe that the gravitational waveforms generated through a simple application of ppBHPT to the comparable mass-ratio cases agree surprisingly well with those from full numerical relativity after a rescaling of the ppBHPT's total mass parameter. This observation and the EMRISur1dq1e4 Surrogate Model will enable data analysis studies in the high-mass-ratio regime, including potential intermediate-mass-ratio signals from LIGO/Virgo and extreme-mass-ratio events of interest to the future space-based observatory LISA.
-
Surrogate Model of hybridized numerical relativity binary black hole waveforms
Physical Review D, 2019Co-Authors: V Varma, Scott E Field, J Blackman, Mark A Scheel, Lawrence E Kidder, Harald P PfeifferAbstract:Numerical relativity (NR) simulations provide the most accurate binary black hole gravitational waveforms, but are prohibitively expensive for applications such as parameter estimation. Surrogate Models of NR waveforms have been shown to be both fast and accurate. However, NR-based Surrogate Models are limited by the training waveforms' length, which is typically about 20 orbits before merger. We remedy this by hybridizing the NR waveforms using both post-Newtonian and effective one-body waveforms for the early inspiral. We present NRHybSur3dq8, a Surrogate Model for hybridized nonprecessing numerical relativity waveforms, that is valid for the entire LIGO band (starting at 20 Hz) for stellar mass binaries with total masses as low as $2.25\text{ }\text{ }{M}_{\ensuremath{\bigodot}}$. We include the $\ensuremath{\ell}\ensuremath{\le}4$ and (5, 5) spin-weighted spherical harmonic modes but not the (4, 1) or (4, 0) modes. This Model has been trained against hybridized waveforms based on 104 NR waveforms with mass ratios $q\ensuremath{\le}8$, and $|{\ensuremath{\chi}}_{1z}|,|{\ensuremath{\chi}}_{2z}|\ensuremath{\le}0.8$, where ${\ensuremath{\chi}}_{1z}$ (${\ensuremath{\chi}}_{2z}$) is the spin of the heavier (lighter) black hole in the direction of orbital angular momentum. The Surrogate reproduces the hybrid waveforms accurately, with mismatches $\ensuremath{\lesssim}3\ifmmode\times\else\texttimes\fi{}{10}^{\ensuremath{-}4}$ over the mass range $2.25\text{ }\text{ }{M}_{\ensuremath{\bigodot}}\ensuremath{\le}M\ensuremath{\le}300\text{ }\text{ }{M}_{\ensuremath{\bigodot}}$. At high masses ($M\ensuremath{\gtrsim}40\text{ }\text{ }{M}_{\ensuremath{\bigodot}}$), where the merger and ringdown are more prominent, we show roughly 2 orders of magnitude improvement over existing waveform Models. We also show that the Surrogate works well even when extrapolated outside its training parameter space range, including at spins as large as 0.998. Finally, we show that this Model accurately reproduces the spheroidal-spherical mode mixing present in the NR ringdown signal.
J Blackman - One of the best experts on this subject based on the ideXlab platform.
-
Surrogate Model of hybridized numerical relativity binary black hole waveforms
Physical Review D, 2019Co-Authors: V Varma, Scott E Field, J Blackman, Mark A Scheel, Lawrence E Kidder, Harald P PfeifferAbstract:Numerical relativity (NR) simulations provide the most accurate binary black hole gravitational waveforms, but are prohibitively expensive for applications such as parameter estimation. Surrogate Models of NR waveforms have been shown to be both fast and accurate. However, NR-based Surrogate Models are limited by the training waveforms' length, which is typically about 20 orbits before merger. We remedy this by hybridizing the NR waveforms using both post-Newtonian and effective one-body waveforms for the early inspiral. We present NRHybSur3dq8, a Surrogate Model for hybridized nonprecessing numerical relativity waveforms, that is valid for the entire LIGO band (starting at 20 Hz) for stellar mass binaries with total masses as low as $2.25\text{ }\text{ }{M}_{\ensuremath{\bigodot}}$. We include the $\ensuremath{\ell}\ensuremath{\le}4$ and (5, 5) spin-weighted spherical harmonic modes but not the (4, 1) or (4, 0) modes. This Model has been trained against hybridized waveforms based on 104 NR waveforms with mass ratios $q\ensuremath{\le}8$, and $|{\ensuremath{\chi}}_{1z}|,|{\ensuremath{\chi}}_{2z}|\ensuremath{\le}0.8$, where ${\ensuremath{\chi}}_{1z}$ (${\ensuremath{\chi}}_{2z}$) is the spin of the heavier (lighter) black hole in the direction of orbital angular momentum. The Surrogate reproduces the hybrid waveforms accurately, with mismatches $\ensuremath{\lesssim}3\ifmmode\times\else\texttimes\fi{}{10}^{\ensuremath{-}4}$ over the mass range $2.25\text{ }\text{ }{M}_{\ensuremath{\bigodot}}\ensuremath{\le}M\ensuremath{\le}300\text{ }\text{ }{M}_{\ensuremath{\bigodot}}$. At high masses ($M\ensuremath{\gtrsim}40\text{ }\text{ }{M}_{\ensuremath{\bigodot}}$), where the merger and ringdown are more prominent, we show roughly 2 orders of magnitude improvement over existing waveform Models. We also show that the Surrogate works well even when extrapolated outside its training parameter space range, including at spins as large as 0.998. Finally, we show that this Model accurately reproduces the spheroidal-spherical mode mixing present in the NR ringdown signal.
-
numerical relativity waveform Surrogate Model for generically precessing binary black hole mergers
Physical Review D, 2017Co-Authors: J Blackman, Scott E Field, Mark A Scheel, Chad R Galley, Christian D Ott, Michael Boyle, Lawrence E Kidder, Harald P PfeifferAbstract:A generic, noneccentric binary black hole (BBH) system emits gravitational waves (GWs) that are completely described by seven intrinsic parameters: the black hole spin vectors and the ratio of their masses. Simulating a BBH coalescence by solving Einstein’s equations numerically is computationally expensive, requiring days to months of computing resources for a single set of parameter values. Since theoretical predictions of the GWs are often needed for many different source parameters, a fast and accurate Model is essential. We present the first Surrogate Model for GWs from the coalescence of BBHs including all seven dimensions of the intrinsic noneccentric parameter space. The Surrogate Model, which we call NRSur7dq2, is built from the results of 744 numerical relativity simulations. NRSur7dq2 covers spin magnitudes up to 0.8 and mass ratios up to 2, includes all l≤4 modes, begins about 20 orbits before merger, and can be evaluated in ∼50 ms. We find the largest NRSur7dq2 errors to be comparable to the largest errors in the numerical relativity simulations, and more than an order of magnitude smaller than the errors of other waveform Models. Our Model, and more broadly the methods developed here, will enable studies that were not previously possible when using highly accurate waveforms, such as parameter inference and tests of general relativity with GW observations.
-
a Surrogate Model of gravitational waveforms from numerical relativity simulations of precessing binary black hole mergers
Physical Review D, 2017Co-Authors: J Blackman, Scott E Field, Mark A Scheel, Chad R Galley, Daniel A Hemberger, P Schmidt, R J E SmithAbstract:We present the first Surrogate Model for gravitational waveforms from the coalescence of precessing binary black holes. We call this Surrogate Model NRSur4d2s. Our methodology significantly extends recently introduced reduced-order and Surrogate Modeling techniques, and is capable of directly Modeling numerical relativity waveforms without introducing phenomenological assumptions or approximations to general relativity. Motivated by GW150914, LIGO’s first detection of gravitational waves from merging black holes, the Model is built from a set of 276 numerical relativity (NR) simulations with mass ratios q ≤ 2, dimensionless spin magnitudes up to 0.8, and the restriction that the initial spin of the smaller black hole lies along the axis of orbital angular momentum. It produces waveforms which begin ∼ 30 gravitational wave cycles before merger and continue through ringdown, and which contain the effects of precession as well as all l∈{2,3} spin-weighted spherical-harmonic modes. We perform cross-validation studies to compare the Model to NR waveforms not used to build the Model and find a better agreement within the parameter range of the Model than other, state-of-the-art precessing waveform Models, with typical mismatches of 10^(-3). We also construct a frequency domain Surrogate Model (called NRSur4d2s_FDROM) which can be evaluated in 50 ms and is suitable for performing parameter estimation studies on gravitational wave detections similar to GW150914.
Qingfu Zhang - One of the best experts on this subject based on the ideXlab platform.
-
a multi fidelity Surrogate Model assisted evolutionary algorithm for computationally expensive optimization problems
Journal of Computational Science, 2016Co-Authors: Bo Liu, Slawomir Koziel, Qingfu ZhangAbstract:Integrating data-driven Surrogate Models and simulation Models of different accuracies (or fidelities) in a single algorithm to address computationally expensive global optimization problems has recently attracted considerable attention. However, handling discrepancies between simulation Models with multiple fidelities in global optimization is a major challenge. To address it, the two major contributions of this paper include: (1) development of a new multi-fidelity Surrogate-Model-based optimization framework, which substantially improves reliability and efficiency of optimization compared to many existing methods, and (2) development of a data mining method to address the discrepancy between the low- and high-fidelity simulation Models. A new efficient global optimization method is then proposed, referred to as multi-fidelity Gaussian process and radial basis function-Model-assisted memetic differential evolution. Its advantages are verified by mathematical benchmark problems and a real-world antenna design automation problem.
-
a gaussian process Surrogate Model assisted evolutionary algorithm for medium scale expensive optimization problems
IEEE Transactions on Evolutionary Computation, 2014Co-Authors: Bo Liu, Qingfu Zhang, Georges GielenAbstract:Surrogate Model assisted evolutionary algorithms (SAEAs) have recently attracted much attention due to the growing need for computationally expensive optimization in many real-world applications. Most current SAEAs, however, focus on small-scale problems. SAEAs for medium-scale problems (i.e., 20-50 decision variables) have not yet been well studied. In this paper, a Gaussian process Surrogate Model assisted evolutionary algorithm for medium-scale computationally expensive optimization problems (GPEME) is proposed and investigated. Its major components are a Surrogate Model-aware search mechanism for expensive optimization problems when a high-quality Surrogate Model is difficult to build and dimension reduction techniques for tackling the “curse of dimensionality.” A new framework is developed and used in GPEME, which carefully coordinates the Surrogate Modeling and the evolutionary search, so that the search can focus on a small promising area and is supported by the constructed Surrogate Model. Sammon mapping is introduced to transform the decision variables from tens of dimensions to a few dimensions, in order to take advantage of Gaussian process Surrogate Modeling in a low-dimensional space. Empirical studies on benchmark problems with 20, 30, and 50 variables and a real-world power amplifier design automation problem with 17 variables show the high efficiency and effectiveness of GPEME. Compared to three state-of-the-art SAEAs, better or similar solutions can be obtained with 12% to 50% exact function evaluations.
-
self adaptive lower confidence bound a new general and effective prescreening method for gaussian process Surrogate Model assisted evolutionary algorithms
Congress on Evolutionary Computation, 2012Co-Authors: Bo Liu, Qingfu Zhang, F V Fernandez, Georges GielenAbstract:Surrogate Model assisted evolutionary algorithms are receiving much attention for the solution of optimization problems with computationally expensive function evaluations. For small scale problems, the use of a Gaussian Process Surrogate Model and prescreening methods has proven to be effective. However, each commonly used prescreening method is only suitable for some types of problems, and the proper prescreening method for an unknown problem cannot be stated beforehand. In this paper, the four existing prescreening methods are analyzed and a new method, called self-adaptive lower confidence bound (ALCB), is proposed. The extent of rewarding the prediction uncertainty is adjusted on line based on the density of samples in a local area and the function properties. The exploration and exploitation ability of prescreening can thus be better balanced. Experimental results on benchmark problems show that ALCB has two main advantages: (1) it is more general for different problem landscapes than any of the four existing prescreening methods; (2) it typically can achieve the best result among all available prescreening methods.
