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 112 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.
-
KLIP: Localized distribution shift detection via KL-divergence with diffusion priors in inverse problems
… detection metric based on the Kullback-Leibler divergence between the diffusion prior and the posterior distribution, that (i) does not require any calibration data or knowledge of the shifted distribution, and (ii) can detect whole images as OOD as well as localize OOD patches within an image. …
-
Recommending Answers to Math Questions Using KL-Divergence and the Approximate XML Tree Matching Approach
… in answering a Math question. MaRec (i) applies KL-divergence to rank the textual content of a potential answer A with respect to the textual content of a Math question Q, and (ii) together with the representation of the Math formulas in Q and A as XML trees determines their subtree matching …
-
Some Advances in Nonparametric Statistics
… posterior contraction rates in Kullback-Leibler (KL) divergence, where I am motivated by the dismatch between KL divergence and Hellinger distance and develop a posterior contraction theory entirely based on KL divergence</p>
-
Policy Optimization with f-Divergence Regularization
… algorithms based on the Kullback–Leibler (KL) divergence. In this thesis, we extend previous work by using a more general form of divergence, the f-divergence, and design a new family of algorithms that can improve the learning policy with theoretical improvement guarantees. Our method, …
-
Sensitivity Testing Using Expectiles with Applications in Extremes
… risk measures along with the Kullback–Leibler divergence (KL divergence) as a measure of discrepancy between the baseline probability measure and the stressed probability measure. An expansion of Reverse Sensitivity Testing is provided to include both a coherent and elicitable risk measure; …
-
Donsker-Varadhan policy matching for reward-free offline reinforcement learning
… This thesis studies an actor-to-behavior KL version of this idea using the Donsker–Varadhan representation of KL divergence. In contrast to behavior cloning’s behavior-to-actor KL direction, this actor-to-behavior direction can avoid the action-averaging problem. A reward-augmented …
-
DR-VAE: Improving VAE with Density Ratio Estimation
… with the density ratio loss which is based on KL divergence to learn the density ratio estimator adversarially. In the second step, it is trained with the density ratio loss and vanilla VAE loss jointly. Then, we designed different methods to further improve generation and reconstruction, …
-
Covariance Selection Quality and Approximation Algorithms
… a distance measure such as the Kullback-Leibler (KL) divergence between the original distribution and the model distribution to quantify the quality of approximated model distribution. Although the KL divergence is minimized to obtain model approximation in many cases, there are other measures and …
-
A Kullback-Leiber Divergence Filter for Anomaly Detection in Non-Destructive Pipeline Inspection
… unfiltered. In this thesis, a Kullback-Leibler (KL) Divergence filter is proposed to detect signals with relatively high information content, namely anomalies, within data series. The data is generated by using the model of a broad class of proximity sensors that apply to devices commonly used in …
-
EFFICIENT GEOMETRIC ALGORITHMS FOR STOCHASTIC AND CATEGORICAL DATA
… local-motion model, using the Kullback-Leibler (KL) divergence to bound the information loss over time. In the second part, we address "spatial uncertainty" by developing classifiers for data constrained to bounded domains, such as the probability simplex. We investigate Support Vector Machines …
-
Model-Free Robust Reinforcement Learning with Sample Complexity Analysis
… sets defined by total variation, Chi-square divergence, and KL divergence, and provide finite sample analyses under all three cases. Remarkably, our algorithms represent the first model-free DR-RL approach featuring finite sample complexity for total variation and Chi-square divergence …
-
Error and f -Divergence Analysis of Generative Adversarial Network
… of error and estimation bounds of various f-divergence metrics in the context of generative adversarial networks (GANs). The error convergence rate is developed and explained by a class of functions with the discriminator and generator neural networks. The new class of functions is uniformly …
-
An Instance-Based Learning Statistical Framework for One-Shot and Few-Shot Human Action Recognition
… Gaussian mixture models, and information divergence. We first aim to obtain accurate representations of the human movements/actions by clustering the results given by GF-OF using K-means method of vector quantization. We then proceed by representing the result of one instance of each …
-
An Instance-Based Learning Statistical Framework for One-Shot and Few-Shot Human Action Recognition
… Gaussian mixture models, and information divergence. We first aim to obtain accurate representations of the human movements/actions by clustering the results given by GF-OF using K-means method of vector quantization. We then proceed by representing the result of one instance of each …
-
Statistical and Computational Properties of Variational Inference
… inference is to minimize the Kullback-Leibler (KL) divergence between the true posterior and mean-field family, the class of product distributions over the model parameters $\mathcal{Q}=\{q(\theta)=q_1(\theta_1)q_2(\theta_2)\cdots q_d(\theta_d) \}$. The variational approximation to the posterior …
-
Cyber-Secure Distributed Control of Microgrids with Improved Communication and Control Protocols
… cybersecurity of such systems, Kullback-Leibler (KL) divergence-based and machine learning-based detection schemes against false data injection (FDI) attacks are proposed. A KL divergence-based strategy locates cyberattacks on a DG by comparing its probability distribution of measurement (e.g., …
-
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 …
Page 1 of 6