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 39 for “"Minimax Optimization"”.
-
Understanding Minimax Optimization in Modern Machine Learning
… formulation of adversarial training is through minimax optimization, or smooth games in a broader sense. In minimax optimization, we have a bi-variate objective function. The goal is to minimize the objective function with respect to one variable, and to maximize the objective function with …
-
Novel first-order methods for bilevel and minimax optimization.
Bilevel and minimax optimization problems arise in various fields, including machine learning, game theory, and decision science. This thesis highlights the underlying connections between constrained minimax and bilevel optimization and develops novel first-order methods with strong theoretical …
-
DIFFERENTIAL EVOLUTION-BASED METHODS FOR NUMERICAL OPTIMIZATION
… in solving single-objective, multi-objective and minimax optimization problems. First, a multiple exponential recombination strategy is proposed to fill the research gap in DE crossover operator development. The new strategy is able to inherit all the main advantages of existing crossover …
-
Efficient Optimization Algorithms for Nonconvex Machine Learning Problems
… enabled the creation of remarkable AI products. Optimization, as the core of machine learning, becomes especially crucial because most machine learning problems can ultimately be formulated as optimization problems, which require minimizing a loss function with respect to model parameters based …
-
Robust Control of Stochastic Nonlinear Systems
The third topic studied involves the constrained minimax optimization problem for a class of stochastic nonlinear systems in strict-feedback form, where in addition to the standard Wiener process there is a norm-bounded unknown disturbance driving the system. The bound on the disturbance is a …
-
Minimax System Modelling and Design
… Computer-aided system modelling and design for minimax objectives have been considered in detail. A new algorithm for minimax approximation, called the grazor search method, has been proposed and successfully used on a number of network design problems to test the reliability and efficiency of …
-
Minimax System Modelling and Design
<p>Computer-aided system modelling and design for minimax objectives have been considered in detail. A new algorithm for minimax approximation, calied the grazor search method, has been proposed and successfully used on a number of network design problems to test the reliability and efficiency of …
-
Some Extensions on the Reach of First-Order Optimization Theory
… thesis concerns the foundations of first-order optimization theory. In recent years, these methods have found tremendous success in a wide range of domains due to their incredibly scalable nature. We aim to extend the reach of first-order optimization guarantees, lessening the gap between …
-
On the computation of the cosine measure in high dimensions
… class of algorithms to solve derivative-free optimization problems. These methods use a set of vectors known as search directions to compute trial points in order to seek function value decrease. Often, the convergence rate of these methods depend on a value known as the cosine measure, which …
-
Secure State Estimation in the Presence of False Information Injection Attacks
… the attacker and the defender is modeled from a minimax perspective, in which the attacker tries to maximize the cost function. On the other hand, the defender tries to optimize the detection threshold selection to minimize the cost function. We consider that the attacker will attack with …
-
Discrete and Continuous Optimization for Collaborative and Multi-task Learning
… challenges of robust collaborative learning and optimization in both discrete and continuous domains. With the ever-increasing scale of data and the growing demand for effective distributed learning, a multitude of obstacles emerge, including communication limitations, resilience to failures and …
-
Kinematic isotropy and robot design optimization using a genetic algorithm method
… maximum one. This strategy illustrates in fact a minimax optimization problem. A "Genetic Algorithm" has been developed to optimize the minimax problem in order to find optimal design parameters such as link lengths of the best isotropic robot configurations at optimal working points of the …
-
Utilizing multi-commodity flow formulations to solve network protection problems
… flow formulations into larger multi-level (e.g., minimax) optimization models. ... The last study examines network fortification models that are able to differentiate between failures that are random (e.g., caused by nature) and strategic network failures (e.g., caused by terrorist activities) …
-
Analysis of Transient and Steady State Vehicle Handling with Torque Vectoring
… force allocation strategy is formulated as a minimax optimization problem. A two-track vehicle model is simulated for this strategy, and it verified the analytical proof by displaying neutralsteering behavior.
-
Wideband Digital Filter-and-Sum Beamforming with Simultaneous Correction of Dispersive Cable and Antenna Effects
… are derived. One solution is found via minimax optimization. To assess feasibility, the cost is analyzed in terms of filter length. These designs are considered in the context of LWA1, the first ``station'' of the Long Wavelength Array (LWA) radio telescope, consisting of 512 bowtie-type …
-
Design and Modelling of Microwave Circuits Using Optimization Methods
… modelling of microwave circuits using efficient minimax and ℓ₁ optimization techniques.</p> <p>Recent algorithms for nonlinear minimax and ℓ₁ for the particular applications of this thesis. Efficient gradient approximation techniques applicable to both minimax and ℓ₁ optimization are …
-
Selected Topics in Network Optimization: Aligning Binary Decision Diagrams for a Facility Location Problem and a Search Method for Dynamic Shortest Path Interdiction
… work deals with three different combinatorial optimization problems: minimizing the total size of a pair of binary decision diagrams (BDDs) under a certain structural property, a variant of the facility location problem, and a dynamic version of the Shortest-Path Interdiction (DSPI) problem. …
Page 1 of 2