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 3909 for “"Robustness"”.
-
Robustness in Bayesian Inference
Made available in DSpace on 2014-12-13T18:22:18Z (GMT). No. of bitstreams: 1 8009105.pdf: 3493399 bytes, checksum: 88facf4ec77a9a0c95fec3b9fb79bb15 (MD5) Previous issue date: 1979
-
Adversarial robustness without perturbations
… light on additional properties relating model robustness and input-gradients of unperturbed images, such as asymmetric color statistics. Suprisingly, we also show significant adversarial robustness may be obtained by simply conditioning gradients to focus on image edges, without explicit …
-
Robustness of Variable Length Codes
The aim of this thesis is to determine the robustness of certain variable length codes in the presence of channel errors. The codes studied are: Huffman, Huffman equivalent, and T-codes. The algorithm used to construct each code is presented, together with appropriate methods of modifying the …
-
Robustness of Bayesian Nash Equilibria
As an application, I show how the mechanism design problem is altered by allowing perturbations in the information structure.
-
Robustness of bond portfolio optimisation
Korn and Koziol (2006) apply the Markowitz (1952) mean-variance framework to bond portfolio selection by proposing the use of term structure models to estimate the time-varying moments of bond returns. Duffee (2002) introduces a distinction between completely affine and essentially affine term …
-
Architecting complex systems for robustness
… cost has already been committed. Addressing robustness and the "ilities" at the architecture level may be more effective because it is the earliest and highest leverage point in the product development process. Furthermore, some system architectures are inherently more robust than others. In …
-
Enhancing network robustness via shielding
Shielding critical links enhances network robustness and provides a new way of designing robust networks. We first consider shielding critical links to guarantee network connectivity after any failure under geographical and general failure models. We develop a mixed integer linear program (MILP) to …
-
Understanding Adversarial Robustness in Deep Learning
This thesis studies the adversarial robustness of deep learning models. Our investigation covers various aspects of this phenomenon, including the development of two new defense algorithms, two new attack algorithms, a novel definition of hierarchical adversarial robustness, and an analysis of how …
-
Robustness and Reliability of Federated Learning
… we focus on two of the most important ones: robustness and reliability. In FL, attacks or faults may occur on each client, and it is crucial that the system is robust to these problems. Furthermore, clients may be unreliable and become unavailable at each point, so FL needs to withstand these …
-
Breeding for robustness in maternal sheep.
A favourable phenotypic relationship between ewe body condition and reproduction has been well reported in literature with producers managing ewe condition to improve reproductive performance. This thesis explores the genetic variation of ewe body composition across her production life and the …
-
Robustness in Feedback Systems (Frequency Domain)
The research in this dissertation is motivated by the basic question "What can and cannot be accomplished by feedback control?" In particular, this dissertation shall address three basic issues: (a) Determining which types of controllers are optimal for certain classes of control problems, (b) …
-
The robustness of H-infinity control
… stability margin, to serve as a measure of this robustness. A fragile controller is defined as a controller that is very sensitive to changes in its controller coefficients and any small change from the nominal controller will result in closed loop instability. This type of controller will have a …
-
Robustness in large-scale random networks
… rules to relate basic network parameters to robustness. Second, we establish analytical results for the length of backup paths for path and link-based protection schemes rather than for the efficiency of backup capacity, upon which most studies concentrate. Finally, we develop a unified …
-
Uncertainty & robustness for single-cell studies
… analyses incorporate notions of uncertainty and robustness to guide their interpretation and inform future decision making. This thesis makes two main advances in facilitating coherent, actionable quantification of uncertainty and robustness for single-cell studies. First, we provide a framework …
-
Efficient computational methods for robustness analysis
… provides a framework for systematically checking robustness properties of large complex dynamical systems. In IQC analysis, the system to be analyzed is represented as a nominal, Linear Time-Invariant (LTI) subsystem interconnected with a perturbation term. The perturbation is characterized in …
-
GENERALIZING ROBUSTNESS VERIFICATION FOR MACHINE LEARNING
Verifying robustness of neural networks given a specified threat model is a fundamental yet challenging task. Although a lot of work has been done to quantify the robustness of DNN’s to ℓₚ norm bounded adversarial attacks there are still a few gaps between available guarantees and those needed in …
-
Network layer protocols with Byzantine robustness
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1988.
-
Essays in Econometrics: Nonparametrics and Robustness
This thesis consists of three chapters. In each chapter I consider a particular problem in econometrics with implications for applied research, and in each case I attempt to solve that problem. In Chapter 1 I consider the task of inferring causal effects when only `proxy controls' are available. …
-
Increasing the robustness of networked systems
What popular news do you recall about networked systems? You've probably heard about the several hour failure at Amazon's computing utility that knocked down many startups for several hours, or the attacks that forced the Estonian government web-sites to be inaccessible for several days, or you may …
-
Learning Through the Lens of Robustness
… requirement can give rise to a trade-off between robustness and accuracy. At the same time, the features that robust models rely on turn out to be more aligned with human perception and, in turn, make these models also useful outside the context of reliability. Finally, we move beyond the …
Page 1 of 196