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 19 of 19 for “"Bregman divergence"”.

  1. Convex regression and its extensions to learning a Bregman divergence and difference of convex functions

    … convex regression to learning an arbitrary Bregman divergence and learning a difference of convex functions. We provide approximation guarantees and sample complexity bounds for both these extensions. Furthermore, we provide algorithms to solve the resulting optimization problems based on …

    bu Repository record for Convex regression and its extensions to learning a Bregman divergence and difference of convex functions (opens in a new tab)

  2. Learning vector and functional Bregman divergences for machine learning applications

    Functional Bregman divergences are an important class of divergences in machine learning that generalize classical Bregman divergences. Functional Bregman divergences can allow one to define a notion of similarity between both sample points and distributions. This class of divergences includes many …

    bu Repository record for Learning vector and functional Bregman divergences for machine learning applications (opens in a new tab)

  3. Towards smarter, safer, and swifter generative AI: adapting, guarding, and accelerating diffusion models

    … foundation of DMs through the lens of Bregman divergence, extending their applicability to count and range-bounded data domains. We further enhance model intelligence by introducing a dense reward perspective for preference alignment, prioritizing the formative early steps of the …

    texas Repository record for Towards smarter, safer, and swifter generative AI: adapting, guarding, and accelerating diffusion models (opens in a new tab)

  4. Online EM for Exponential Family Distributions

    … descent updates. This method employs custom Bregman divergences for parameter updates and allows for the processing of one unit of data at each iteration. Our second contribution is an improved version of the EM algorithm for exponential family distributions. In this case, we replace the …

    mcmaster Repository record for Online EM for Exponential Family Distributions (opens in a new tab)

  5. Geometry and Optimization of Relative Arbitrage

    … Part I. It extends the dually flat geometry of Bregman divergence studied by S. Amari and others, leading to plenty of problems for further study.

    washington Repository record for Geometry and Optimization of Relative Arbitrage (opens in a new tab)

  6. Exploration and Primal-dual Methods in Bandits and Reinforcement Learning

    … policy optimization, we propose using dual Bregman divergence instead of the common Euclidean norm to measure similarity in dual space, resulting in the first policy optimization framework with both fast theoretical convergence and superior practical performance. Collectively, these …

    washington Repository record for Exploration and Primal-dual Methods in Bandits and Reinforcement Learning (opens in a new tab)

  7. Scalable clustering algorithms

    … a large class of distance measures known as Bregman divergences. We present both hard and soft-clustering algorithms using Bregman divergences. By establishing a bijection between regular exponential family distributions and regular Bregman divergences, we note that Bregman soft clustering …

    texas Repository record for Scalable clustering algorithms (opens in a new tab)

  8. Learning to rank in supervised and unsupervised settings using convexity and monotonicity

    … is measured geometrically by a suitable Bregman divergence between the consensus rank and the ranks induced by item specific distributions Real world deployed ranking methods need to be resistant to spam, a particularly sophisticated type of which is link-spam. A popular class of …

    texas Repository record for Learning to rank in supervised and unsupervised settings using convexity and monotonicity (opens in a new tab)

  9. GEOMETRIC APPROACHES TO DISCRIMINATIVE TRAINING

    … of NGD. The loss functions, defined by Bregman divergence, generalizes the log-likelihood objective and can be easily coupled with NGD for optimization. The proposed framework is flexible, allowing us to choose proper convex functions that leads to better training performance. Finally, …

    jhu Repository record for GEOMETRIC APPROACHES TO DISCRIMINATIVE TRAINING (opens in a new tab)

  10. Advancing Distributional Off-policy Evaluation in Reinforcement Learning

    … (FDE). We have shown that the functional Bregman divergence, which has close relationship with proper scoring rule, serves as an appropriate candidate for building the objective functions. Since proper scoring rule is a widely-studied concept in the realm of statistics, this opens the door …

    tamu Repository record for Advancing Distributional Off-policy Evaluation in Reinforcement Learning (opens in a new tab) Embargoed until 2027-08-01

  11. Advancing Distributional Off-policy Evaluation in Reinforcement Learning

    … (FDE). We have shown that the functional Bregman divergence, which has close relationship with proper scoring rule, serves as an appropriate candidate for building the objective functions. Since proper scoring rule is a widely-studied concept in the realm of statistics, this opens the door …

    tamu Repository record for Advancing Distributional Off-policy Evaluation in Reinforcement Learning (opens in a new tab) Embargoed until 2027-08-01

  12. Advancing Distributional Off-policy Evaluation in Reinforcement Learning

    … (FDE). We have shown that the functional Bregman divergence, which has close relationship with proper scoring rule, serves as an appropriate candidate for building the objective functions. Since proper scoring rule is a widely-studied concept in the realm of statistics, this opens the door …

    tamu Repository record for Advancing Distributional Off-policy Evaluation in Reinforcement Learning (opens in a new tab) Embargoed until 2027-08-01

  13. Advancing Distributional Off-policy Evaluation in Reinforcement Learning

    … (FDE). We have shown that the functional Bregman divergence, which has close relationship with proper scoring rule, serves as an appropriate candidate for building the objective functions. Since proper scoring rule is a widely-studied concept in the realm of statistics, this opens the door …

    tamu Repository record for Advancing Distributional Off-policy Evaluation in Reinforcement Learning (opens in a new tab) Embargoed until 2027-08-01

  14. Advancing Distributional Off-policy Evaluation in Reinforcement Learning

    … (FDE). We have shown that the functional Bregman divergence, which has close relationship with proper scoring rule, serves as an appropriate candidate for building the objective functions. Since proper scoring rule is a widely-studied concept in the realm of statistics, this opens the door …

    tamu Repository record for Advancing Distributional Off-policy Evaluation in Reinforcement Learning (opens in a new tab) Embargoed until 2027-08-01

  15. Advancing Distributional Off-policy Evaluation in Reinforcement Learning

    … (FDE). We have shown that the functional Bregman divergence, which has close relationship with proper scoring rule, serves as an appropriate candidate for building the objective functions. Since proper scoring rule is a widely-studied concept in the realm of statistics, this opens the door …

    tamu Repository record for Advancing Distributional Off-policy Evaluation in Reinforcement Learning (opens in a new tab) Embargoed until 2027-08-01

  16. A Dynamical Systems Perspective on Optimization Algorithms

    … smooth if we quantify convexity in terms of the Bregman divergence, namely $D_f(x,y) \geq \frac{\mu}{p}\|x - y\|^p $, and consider the classes $\mathcal{F}_L$ and $\mathcal{F}_{\mu,L}$ as the edge cases $p\to\infty$ and $p=2$. More generally, introducing the \emph{modulus of convexity} ($\phi$) …

    penn Repository record for A Dynamical Systems Perspective on Optimization Algorithms (opens in a new tab)

  17. Generalized Maximum Entropy, Convexity and Machine Learning

    … on deformed logarithms are used to construct Bregman divergences, and together these represent a generalization of relative entropy. The framework is analyzed using convex analysis to charac- terize generalized forms of exponential family distributions. Various connections to the existing …

    anu Repository record for Generalized Maximum Entropy, Convexity and Machine Learning (opens in a new tab)

  18. Aggregating credences into a belief

    … Moreover, we study distance minimization with Bregman divergence, utility maximization with strict proper scores, and their relationship. Direct heterogeneous belief aggregation rules will also be proposed and studied regarding threshold, distance and epistemic-utility. We provide a new …

    lmu-germany Repository record for Aggregating credences into a belief (opens in a new tab)

  19. Structured numerical problems in contemporary applications

    … be minimized are the von Neumann and the LogDet Bregman matrix divergences. The algorithm that solves this optimization problem performs matrix updates based on repeated eigendecompositions of diagonal plus rank-one matrices in the case of von Neumann matrix divergence, and Cholesky updates in …

    texas Repository record for Structured numerical problems in contemporary applications (opens in a new tab)