Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 30 for “"Derivative-free"”.
-
Algorithms for Derivative-Free Optimization
… Search (M&S), a new local search algorithm for derivative-free optimization. M&S performs a local search from a given point. The search is guided by identifying descent directions from a quadratic model fitted around the best known point, while using information from other evaluated points. We …
-
Derivative free methods in covariance components estimation
The downhill simplex (DS), Powell's (PO), and Rosenbrock's (RO) algorithm were optimized and applied to estimation of dispersion parameters. The optimization is independent of the log-likelihood function and thus, from the model. The model can accommodate two additive genetic effects and genetic …
-
Derivative-Free Meta-Blackbox Optimization on Manifold
… efficiency and sample complexity of derivative-free optimization. Based on the observation that most practical high-dimensional functions lie on a latent low-dimensional manifold, which can be further shared among problem instances, the proposed method jointly learns the …
-
Derivative-Free Methods for High-Dimensional Optimization with Application to Centrifugal Pump Design
… real-life design problems do not have access to derivative information. For instance, many design problems use open-source or commercial computational fluid dynamics (CFD) simulation codes to evaluate design performance. Although automatic differentiation and adjoints have become increasingly …
-
Adaptive sampling trust-region methods for derivative-based and derivative-free simulation optimization problems
… optimized, and updated iteratively. ASTRO is a derivative-based algorithm and provides almost sure convergence to a first-order critical point with good practical performance. In the second study the Monte Carlo simulation is assumed to provide no direct observations of the function gradient. We …
-
Development of self-adaptive back propagation and derivative free training algorithms in artificial neural networks
Three new iterative, dynamically self-adaptive, derivative-free and training parameter free artificial neural network (ANN) training algorithms are developed. They are defined as self-adaptive back propagation, multi-directional and restart ANN training algorithms. The descent direction in …
-
Geometric numerical integration for optimisation
… theory. Second, motivated by the existence of derivative-free discrete gradients, and seeking to solve nonsmooth optimisation problems and more generally black-box problems, including for parameter optimisation problems, we propose methods based on the Itoh--Abe discrete gradient method for …
-
Peridynamic Modeling of Coupled Mechanical Deformations and Transient Flow in Unsaturated Soils
… equation of motion is replaced by a non-local, derivative free, functional integral. The absence of spatial derivatives leads to a model that is valid everywhere in the simulation domain, including points of discontinuities. Following a similar approach, we developed a moisture flow model where …
-
Variations on bayesian optimization applied to numerical flow simulations
… the efficiency of classical BO and alternative derivative-free methods is compared on a simplified flow case, i.e. drag reduction in the two-dimensional flow around a cylinder. The application of BO to complex flows is then showcased by considering a three-dimensional case at Reynolds number Re …
-
Técnicas de otimização da produção para reservatórios de petróleo: abordagens sem uso de derivadas para alocação dinâmica das vazões de produção e injeção
… o de Busca Direta em Padrões (Pattern Search), o Derivative Free Optimization de Conn et al e o Algoritmo Genético. Os estudos foram aplicados a dois casos de características distintas. O primeiro caso apresenta características bem simples e de fácil controle. O outro caso de aplicação é um modelo …
-
An inverse problem framework for reconstruction of phonon properties using solutions of the Boltzmann transport equation
… that assumption. The proposed method combines a derivative-free optimization method, referred to as the Nelder-Mead algorithm, with a graduated (multi-stage) optimization framework.
-
Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization
Global optimization of expensive, derivative-free black-box functions requires extreme sample efficiency. While Bayesian optimization (BO) is the current state-of-the-art, its performance hinges on surrogate and acquisition function hyperparameters that are often hand-tuned and fail to generalize …
-
Numerical computation of perturbation solutions of nonautonomous systems
… conducted using Galerkin's approximations and a derivative-free analogue of Newton's iteration method. Furthermore, the motion stability of a dynamical system in the neighborhood of the approximate periodic solutions due to the effect of the extraneous forces, introduced by the process of using …
-
Patterns in an elastic bar
… Method (FEM) to approximate the model and the Derivative Free Optimization (DFO) to find the location of the jump.
-
Supervised Calibration and Uncertainty Quantification of Subgrid Closure Parameters using Ensemble Kalman Inversion
… updates alter the dependency of a model on its free parameters, evidence about structural biases is often muddied by the variable influences of inadequately-tuned parameters on the model solution. We elaborate a framework for model development that combines calibration, sensitivity analysis, and …
-
Service ORiented Computing EnviRonment (SORCER) for Deterministic Global and Stochastic Optimization
… algorithm DIRECT, is a highly parallelizable derivative-free deterministic global optimization algorithm. QNSTOP is a parallel quasi-Newton algorithm for stochastic optimization problems. The purpose of integrating VTDIRECT95 and QNSTOP into the SORCER framework is to provide load balancing …
-
Reinforcement learning in continuous state- and action-space
… including gradient-ascent along with other derivative-based and derivative-free numerical optimization methods,and the proposal of two novel algorithms which are based on the application of two alternative action selection methods: NM-SARSA [40] and NelderMead-SARSA. We empirically compare …
-
Novel higher order regularisation methods for image reconstruction
… which the regulariser incorporates second order derivatives or a sophisticated combination of first and second order derivatives. The introduction of higher order derivatives in the regularisation process has been shown to be an advantage over the classical first order case, i.e., total variation …
-
Progress on the Interplay of Machine Learning and Optimization
… We develop a model-based trust-region method for derivative-free optimization problems under noise. Our method, which uses robust and sparse regression to build models of functions, is much more robust and has higher scalability than existing methods.
-
A Large Scale Network Model to Obtain Interwell Formation Characteristics
… values between each node are the unknowns. A derivative free optimization algorithm is utilized to minimize the objective function. Knowing the conductivity of each of the bonds, a two phase problem is formulated and solved in this work to obtain the fractional flow at node interfaces and at …
Page 1 of 2