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 494 for “"Minimax"”.
-
Minimax Controller Design
Made available in DSpace on 2014-12-08T22:24:20Z (GMT). No. of bitstreams: 1 6808211.pdf: 2652815 bytes, checksum: d04c68f8a104d03749ebf93dd02fc765 (MD5) Previous issue date: 1967
-
Best rotated minimax approximation
In this dissertation we consider the minimax approximation of functions f(x) E"C[O, l] rotated about the origin, and the characterization of the optimal rotation, a*, of f in the sense of least minimax error over all possible rotations. The paper divides naturally into two sections: a) Existence, …
-
Contributions to Minimax Statistical Theory
… decision making. We study these problems using minimax analysis, determining the best possible performance against worst-case data and distributions, where the notion of worst-case is problem-specific. The considerable flexibility of this approach facilitates, for example, characterizing …
-
Minimax Adaptive Control and Estimation
This thesis presents five papers on minimax adaptive control and estimation. Minimax adaptive estimation is a framework for output prediction and state estimation that provides a priori computable performance bounds for esti- mators. Minimax adaptive controllers ensure that the closed loop has …
-
Minimax Fairness in Machine Learning
… the best performance for the worst group (i.e., minimax solutions). We study how to achieve minimax Pareto fair solutions when sensitive groups are available at training time, and also when the demographics are completely unknown. We provide experimental results showing how the discussed …
-
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 …
-
Minimax AI within Non-Deterministic Environments
… we used a well-known decision algorithm, minimax, in an attempt to focus on both of these issues while still providing emergent intelligence to the system. Minimax has existed since 1928, and has been proven sound in games of perfect information such as chess, or checkers. We refer to …
-
On bilevel programs and minimax problems
… a growing prevalence of bilevel programs and minimax problems in recent years. In our research, we intricately explore second-order optimality conditions within the realm of bilevel programs and minimax problems. First, we provide a comprehensive exploration of second-order combined approaches …
-
Steganography using the Minimax Eigenvalue Decomposition
… times of a file, can be used as covert channels.;Minimax algebra is known to have applications to machine scheduling, operations research, and image algebra. Raymond Cuninghame-Green provided the groundbreaking work in this area. Minimax algebra provides parallels to linear algebra by extending …
-
A Gradient Algorithm for Minimax Design
Made available in DSpace on 2014-12-08T22:24:37Z (GMT). No. of bitstreams: 1 7000872.pdf: 1008293 bytes, checksum: 260c870d28137831cc6a42b76b7b14b4 (MD5) Previous issue date: 1969
-
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 …
-
Minimax robust designs for misspecified regression models
Minimax robust designs are studied for regression models with possible misspecified response functions. These designs, minimizing the maximum of the mean squared error matrix, can control the bias caused by model misspecification and the desired efficiency through one parameter. Using nonsmooth …
-
Estimation of KL divergence: optimal minimax rate
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2017-02-28 without embargo terms
-
Solving an eigenvalve-eigenvector problem in minimax algebra
… eigenvector problem which is formulated in Minimax Algebra. This example is motivated by the Industrial Machine example which is explained in detail in Chapter 1. Also in Chapter 1 we list the basic definition of the binary operations. Next we give the standard axioms on which Minimax …
Page 1 of 25