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"”.

  1. 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

    uiuc Repository record for Estimation of KL divergence: optimal minimax rate (opens in a new tab)

  2. 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

    uiuc Repository record for KL divergence – based disagreement sampling for multi-fidelity Bayesian optimization (opens in a new tab)

  3. 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.

    uiuc Repository record for Improve KL -Divergence Language Models in Information Retrieval Using Corpus Local Structures (opens in a new tab)

  4. 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 …

    syracuse-diss Repository record for ROBUST KULLBACK-LEIBLER DIVERGENCE AND ITS APPLICATIONS IN UNIVERSAL HYPOTHESIS TESTING AND DEVIATION DETECTION (opens in a new tab)

  5. 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 …

    mit Repository record for Divergence Covering (opens in a new tab)

  6. 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, …

    mit Repository record for Proximal Gradient Algorithms for Gaussian Variational Inference:Optimization in the Bures–Wasserstein Space (opens in a new tab)

  7. 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 …

    mit Repository record for A study of local approximations in information theory (opens in a new tab)

  8. 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 …

    mit Repository record for Mathematical analysis of uncertainty in machine learning and deep learning (opens in a new tab)

  9. 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 …

    mit Repository record for A dynamic key frames approach to object tracking (opens in a new tab)

  10. 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 …

    vt Repository record for Objective Bayesian Analysis of Kullback-Liebler Divergence of two Multivariate Normal Distributions with Common Covariance Matrix and Star-shape Gaussian Graphical Model (opens in a new tab)

  11. 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 …

    mit Repository record for Information contraction and decomposition (opens in a new tab)

  12. 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 …

    umn Repository record for BAYESIAN SEQUENTIAL OPTIMAL EXPERIMENTAL DESIGN FOR INVERSE PROBLEMS USING DEEP REINFORCEMENT LEARNING (opens in a new tab)

  13. 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.

    cambridge Repository record for Statistical models for noise-robust speech recognition (opens in a new tab)

  14. 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 …

    mit Repository record for I-Con: A Unifying Framework for Representation Learning (opens in a new tab)

  15. 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 …

    mit Repository record for An information-theoretic analysis of resampling in Sequential Monte Carlo (opens in a new tab)

  16. 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 …

    uiuc Repository record for Estimating directed information to infer causal relationships between neural spike trains and approximating discrete probability distributions with causal dependence trees (opens in a new tab)

  17. 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).

    mit Repository record for Non-parametric threshold for smoothed empirical Wasserstein distance (opens in a new tab)

  18. 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 …

    cambridge Repository record for Statistical Surrogate Models for Robust Design Optimisation in Reduced Dimension (opens in a new tab)

  19. 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 …

    mit Repository record for Scenario analyzer for real-time Dynamic Transportation Assignment (DTA) systems (opens in a new tab)

  20. 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.

    mit Repository record for Interpolating Spline Curves of Measures (opens in a new tab)

Page 1 of 2