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 4 of 4 for “"Score-based Generative Modeling"”.

  1. A Unified Unsupervised Anomaly Detection Framework with Score-based Generative Modeling for Multivariate Time Series

    … into four main approaches: reconstruction-based, density estimation-based, boundary description-based, and explicit data characteristic modeling-based. Although each of these methodologies has its own advantages, they are also limited by inherent weaknesses that restrict their effectiveness …

    unr Repository record for A Unified Unsupervised Anomaly Detection Framework with Score-based Generative Modeling for Multivariate Time Series (opens in a new tab)

  2. Learning to compress with side information under network constraints and risk sensitivity

    … quantization, compressive sensing, and transform-based codecs, across domains spanning wireless communications and natural images. Yet, as the deployment of such models expands into large-scale, dynamic, and interconnected systems, their design and training face various growing challenges. Beyond …

    texas Repository record for Learning to compress with side information under network constraints and risk sensitivity (opens in a new tab)

  3. Optimization, Sampling, and Generative Modeling on Manifolds

    … and theory for optimization, sampling, and generative modeling on manifolds, with Lie groups as a central object of study. Lie groups are manifolds with additional group structure; when endowed with a left-invariant Riemannian metric they become Riemannian manifolds, a setting that plays a …

    gatech Repository record for Optimization, Sampling, and Generative Modeling on Manifolds (opens in a new tab)