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 13 of 13 for “"Gradient Based Algorithms"”.
-
Permeability Distribution Estimation Based on Semi-Analytical Reservoir Simulator
… simulator, the choice of optimization algorithms to minimize the objective function becomes of vital importance. For our simulator, we considered both gradient based methods and non-gradient based methods. Gradient based algorithms have the big advantage of much faster convergence rate …
-
Geometry of Feedback Control and Learning
… dynamic games, through the lens of first-order algorithms. The developed theories on these topics are largely derived from model-based dynamic programming. Recently there is a surge of interest in constructing optimal control strategies directly, viewing control synthesis by policy gradient …
-
Reductions of ReLU neural networks to linear neural networks and their applications
… behavior of ReLU neural networks trained with gradient descent and the second characterizes their convergence under gradient-based algorithms.
-
High-order tuners for convex optimization : stability and accelerated learning
Iterative gradient-based algorithms have been increasingly applied for the training of a broad variety of machine learning models including large neural-nets. In particular, momentum-based methods, with accelerated learning guarantees, have received a lot of attention due to their provable …
-
Optimization Theory and Machine Learning Practice: Mind the Gap
… data. The process of selecting a good model based on a known dataset requires optimization. In particular, an optimization procedure generates a variable in a constraint set to minimize an objective. This process subsumes many machine learning pipelines including neural network training, …
-
Side scan sonar image formation, restoration and modelling.
… principally with the development of processing algorithms for sonar image enhancement. The thesis is divided into two principal parts. In the first part the statistical properties of side scan sonar images are analysed. Then, based on this analysis, a Maximum A Posteriori (MAP) formulation of …
-
Hybrid And Hierarchical Image Registration Techniques
… classified into two categories: intensity-based and feature-based methods. The primary drawback of the intensity-based approaches is that it may fail unless the two images are misaligned by a moderate difference in scale, rotation, and translation. In addition, intensity-based methods lack …
-
Modeling, Sensitivity Analysis, and Optimization of Hybrid, Constrained Mechanical Systems
… sensitivities for hybrid systems is structured based on jumping conditions for both, the velocity state variables and the sensitivities matrix. The proposed analytical approach is then benchmarked against a known numerical method. The mathematical framework is extended to compute sensitivities …
-
Algorithmic Modifications to a Multidisciplinary Design Optimization Model of Containerships
… sub-problems. But to avail the advantages of gradient-based optimization algorithms, the design problem is molded into a fully continuous problem. The efficiency and effectiveness with which an optimization process achieves the best design depends on how well the design problem is posed for …
-
Intensity Modulated Proton Therapy Optimization Under Uncertainty: Field Misalignment and Internal Organ Motion
… healthy tissues. Compared to conventional photon-based radiation therapy, IMPT is more flexible in delivering radiation dose according to different tumor shapes. However, this flexibility also makes the optimization problems in IMPT harder to solve, e.g., it requires larger memory to store data …
-
Statistical and Algorithmic Thresholds in Spin Glasses
… setting. Part II of this thesis concerns algorithms for optimization and sampling problems on spin glasses. Chapter 5 studies the problem of optimizing the Hamiltonian of a multi-species spherical spin glass. Our main result exactly characterizes the maximum value attainable by a class of …
-
On Ways to Improve Adaptive Filter Performance
… of an adaptive filtering algorithm is evaluated based on its convergence rate, misadjustment, computational requirements, and numerical robustness. We attempt to improve the performance by developing new adaptation algorithms and by using "unconventional" structures for adaptive filters. Part I …
-
Distributed algorithms for networked multi-agent systems: optimization and competition
… pertains to the development of distributed algorithms in the context of networked multi-agent systems. Such engineered systems may be tasked with a variety of goals, ranging from the solution of optimization problems to addressing the solution of variational inequality problems. Two key …