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 15 of 15 for “"Information Geometry"”.
-
Information Geometry For Nonlinear Least-Squares Data Fitting And Calculation Of The Superconducting Superheating Field
… consist of two chapters. First we explore the information geometric properties of least squares data fitting, particularly for so-called "sloppy" models. Second we describe a calculation of the superconducting superheating field, relevant for advancing gradients in particle accelerator …
-
Geometry and Optimization of Relative Arbitrage
… optimal transport, nonparametric statistics and information geometry. Our main object of study is functionally generated portfolio, a family of volatility harvesting investment strategies with remarkable properties. This thesis consists of three parts. Part I gives a convex-analytic treatment of …
-
Climbing Mount Probable
… the relationships between natural selection, information theory, and statistical inference. In particular, a geometric formulation of information theory known as information geometry and its deep connections to evolutionary game theory inform the role of natural selection in evolutionary …
-
I-Con: A Unifying Framework for Representation Learning
… classes of problems. We introduce a single information-theoretic equation that generalizes a large collection of modern loss functions in machine learning. In particular, we introduce a framework that shows that several broad classes of machine learning methods are precisely minimizing an …
-
Towards an Information Theoretic Framework for Evolutionary Learning
… essence of evolutionary learning consists of information flows between the environment and the entities differentially surviving and reproducing therein. Gain or loss of information in individuals and populations due to evolutionary steps should be considered in evolutionary algorithm theory …
-
Extended Entropy Maximisation and Queueing Systems with Heavy-Tailed Distributions
… been suggested within statistical physics and information theory, subject to suitable linear and non-linear system constraints. In both discrete and continuous time domains, new heavy tail analytic performance distributions will be developed, with a focus on those exhibiting the power law …
-
Stochastic processes on graphs with cycles : geometric and variational approaches
… computer vision, artificial intelligence, and information theory. The formalism of graphical models provides a useful language with which to formulate fundamental problems common to all of these fields, including estimation, model fitting, and sampling. For graphs without cycles, known as …
-
Representation learning for regime detection in financial markets
… learning of the causal (reflexive) information geometry underpinning complex (multi-scale) dynamical traded asset systems using an emergent hierarchical correlation structure to characterise evolving macroeconomic market phases. Specifically, we assess the robustness of three toy …
-
Information-centric Algorithms for Feature Extraction in High-Dimensional Sequential Data
… complexity while retaining relevant information. This thesis addresses key challenges in feature extraction for high-dimensional HMMs. Current methods, such as neural networks (NNs), are widely used for nonlinear feature learning but lack mechanisms to prioritize useful features or …
-
Local to global geometric methods in information theory
This thesis treats several information theoretic problems with a unified geometric approach. The development of this approach was motivated by the challenges encountered while working on these problems, and in turn, the testing of the initial tools to these problems suggested numerous refinements …
-
Single-cell multi-omic data analysis with mathematical and statistical methods
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2024-08-01
-
A Differential Geometry-Based Algorithm for Solving the Minimum Hellinger Distance Estimator
Robust estimation of statistical parameters is traditionally believed to exist in a trade space between robustness and efficiency. This thesis examines the Minimum Hellinger Distance Estimator (MHDE), which is known to have desirable robustness properties as well as desirable efficiency properties. …
-
Geometric Methods for Point Estimation
… The second half of this work explores information geometric aspects of covariance matrix estimation. In a regular statistical model the Fisher information metric endows the parameter space with a Riemannian manifold structure. Parameter estimation can therefore also be viewed as problem …
-
Optimisation Methods For Training Deep Neural Networks in Speech Recognition
… To address the issue, this thesis develops the geometry of the underlying function space captured by different realisations of DNN model parameters, and presents the design considerations for an optimisation algorithm to be well defined on this space. Building on this analysis, a novel …