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 “"Stein Variational Gradient Descent"”.

  1. Are Particle-Based Methods the Future of Sampling in Joint Energy Models? A Deep Dive into SVGD and SGLD

    This thesis investigates the integration of Stein Variational Gradient Descent (SVGD) with Joint Energy Models (JEMs), comparing its performance to Stochastic Gradient Langevin Dynamics (SGLD). We incorporated a generative loss term with an entropy component to enhance diversity and a smoothing …

    vt Repository record for Are Particle-Based Methods the Future of Sampling in Joint Energy Models? A Deep Dive into SVGD and SGLD (opens in a new tab)

  2. Strengthening nonparametric Bayesian methods with structured kernels

    … which can either be optimized or inferred, and variational parameters which only requires optimization and no priors. The inducing point locations, however, exist somewhat outside this dichotomy, but the common practice is to simply find point estimates via optimization. We demonstrate that a …

    aalto Repository record for Strengthening nonparametric Bayesian methods with structured kernels (opens in a new tab)

  3. Deep Generative Models for Image Representation Learning

    … captions. The model is efficiently learned using variational autoencoder. A multilayered (deep) convolutional dictionary representation is employed as a decoder of the</p><p>latent image features. Stochastic unpooling is employed to link consecutive layers in the image model, yielding top-down …

    duke Repository record for Deep Generative Models for Image Representation Learning (opens in a new tab)

  4. Towards Robust Deep Neural Networks: Query Efficient Black-Box Adversarial Attacks and Defences

    … decision-based attacks employing approximate gradient estimation or random search methods. These attacks aim at discovering lp>0 constraint adversarial instances, dubbed dense attacks. The research then develops a robust class of query efficient attacks capable of avoiding entrapment in a …

    adelaide Repository record for Towards Robust Deep Neural Networks: Query Efficient Black-Box Adversarial Attacks and Defences (opens in a new tab)