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 37 for “"KL divergence"”.
-
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
-
KL divergence – based disagreement sampling for multi-fidelity Bayesian optimization
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms
-
Improve KL -Divergence Language Models in Information Retrieval Using Corpus Local Structures
In summary, this thesis studies KL-divergence from different perspectives and proposes several new models to address the existing problems in KL-divergence language models. It results in more effective retrieval models, which should potentially benefit all retrieval applications.
-
ROBUST KULLBACK-LEIBLER DIVERGENCE AND ITS APPLICATIONS IN UNIVERSAL HYPOTHESIS TESTING AND DEVIATION DETECTION
<p>The Kullback-Leibler (KL) divergence is one of the most fundamental metrics in information theory and statistics and provides various operational interpretations in the context of mathematical communication theory and statistical hypothesis testing. The KL divergence for discrete distributions …
-
Divergence Covering
… probability distributions is Kullback-Leibler (KL) divergence. Both topics have been massively studied in various contexts, and in this thesis we focus on studying the problem when the two concepts are combined. This combination yields interesting techniques for providing useful bounds on a …
-
Proximal Gradient Algorithms for Gaussian Variational Inference:Optimization in the Bures–Wasserstein Space
… π by minimizing the Kullback–Leibler (KL) divergence to π over the space of Gaussians. In this work, we develop the (Stochastic) Forward-Backward Gaussian Variational Inference (FB–GVI) algorithm to solve Gaussian VI. Our approach exploits the composite structure of the KL divergence, …
-
A study of local approximations in information theory
… but nonlinear definition of Kullback-Leibler (KL) divergence between two probability distributions. Local information theory addresses this issue by assuming all distributions of interest are perturbations of certain reference distributions, and then approximating KL divergence with a squared …
-
Mathematical analysis of uncertainty in machine learning and deep learning
… of the framework due to the property of the KL divergence, and review the modified algorithm using o-divergence which generalizes the KL divergence. We also study a confidence band to assess uncertainty of a kernel ridge regression estimator. We propose the formulation to obtain a confidence …
-
A dynamic key frames approach to object tracking
… estimation from observations. The algorithm uses KL-divergence as a metric to identify the frames that contribute the most information to estimation of the system's current state. The algorithm is first presented in a numerical optimization framework and then developed as an extension to the …
-
Objective Bayesian Analysis of Kullback-Liebler Divergence of two Multivariate Normal Distributions with Common Covariance Matrix and Star-shape Gaussian Graphical Model
… random posteriors of the Kullback-Liebler (KL) divergence of the two multivariate normal populations, which is proportional to the distance between the two means, weighted by the common precision matrix. We use the Cholesky decomposition for re-parameterization of the precision matrix. The …
-
Information contraction and decomposition
… In information theory, the contraction of f-divergences, such as Kullback-Leibler (KL) divergence, X²-divergence, and total variation (TV) distance, through channels (or the contraction of mutual f-information along Markov chains) is quantitatively captured by the well-known data processing …
-
BAYESIAN SEQUENTIAL OPTIMAL EXPERIMENTAL DESIGN FOR INVERSE PROBLEMS USING DEEP REINFORCEMENT LEARNING
… compared to other baseline algorithms. Using KL-divergence as a measure of information gain, we construct objectives to maximize information gain for batch design, greedy design, black-box Bayesian optimization, multi-armed bandit optimization, dynamic programming, approximate dynamic …
-
Statistical models for noise-robust speech recognition
… of compensation techniques, based on the KL divergence to the ideal compensation for one component. The KL divergence proves to predict the word error rate well. This technique also makes it possible to evaluate the impact of approximations that standard compensation schemes make.
-
I-Con: A Unifying Framework for Representation Learning
… methods are precisely minimizing an integrated KL divergence between two conditional distributions: the supervisory and learned representations. This viewpoint exposes a hidden information geometry underlying clustering, spectral methods, dimensionality reduction, contrastive learning, and …
-
An information-theoretic analysis of resampling in Sequential Monte Carlo
… give convergence rates of the Kullback-Leibler divergence KL ... as well as necessary and sufficient conditions for the resampled version of P to asymptotically dominate the non-resampled version from this KL divergence perspective. Versions of these results are given for both the full joint and …
-
Estimating directed information to infer causal relationships between neural spike trains and approximating discrete probability distributions with causal dependence trees
… fi nding the ""best"" approximation (in terms of KL divergence) of a full, joint distribution over a set of random processes, using a causal dependence tree distribution. Chow and Liu's procedure had been shown to be equivalent to maximizing a sum of mutual informations, and the procedure …
-
Non-parametric threshold for smoothed empirical Wasserstein distance
… rate between the W2 distance squared and the KL divergence, resulting in the failure of 𝑇₂-transportation inequality when 𝜎 < 𝐾, hence also resolving the open problem in [17] about whether 𝐾 < 𝜎 is necessary in proving whether the log-Sobolev inequality holds for P * 𝒩 (0, 𝜎²).
-
Statistical Surrogate Models for Robust Design Optimisation in Reduced Dimension
… is measured using the Kullback-Leibler (KL) divergence. Stochastic gradient descent is used to minimise the KL divergence to jointly learn the variational parameters and other parameters of the statistical model. The accuracy, efficiency, and versatility of the RDVGP surrogate is …
-
Scenario analyzer for real-time Dynamic Transportation Assignment (DTA) systems
… Tripod) in the Boston CBD network. The k-NN and KL divergence matching algorithms are tested for a simulation period of 6 AM - 9 PM. Results indicate that the scenario analyzer with k-NN outperforms KLD algorithm probably because KLD need more data points to fully-develop the time-series …
-
Interpolating Spline Curves of Measures
… certain interpolation constrains and minimize a KL divergence, in analogy with the Schrödinger bridge problem. We conclude with an extension of our methods to the case of unbalanced measures in the Wasserstein-Fisher-Rao space.
Page 1 of 2