Back to search

Rochester Institute of Technology

Stochastic Variational Autoencoder

Abstract

dc:description.abstract

This work explores a novel generative modeling approach inspired by variational autoencoders (VAEs). Traditional VAEs rely on a recognition model (encoder) that approximates the latent posterior with a single gaussian distribution for each input, limiting their flexibility in capturing complex data distributions. In contrast, we propose a modified recognition model that utilizes stochastic mixtures of gaussians, allowing for a more expressive latent representation. By leveraging stochastic neural networks within the VAE framework, we aim to achieve a tighter evidence lower bound (ELBO) on the log-likelihood of the data. Our approach is a preliminary investigation to enhance the latent space structure and improve generative performance by incorporating richer uncertainty modeling.

Degree

thesis:*
Name thesis:degree_name
Computer Science (MS)
Level thesis:degree_level
Thesis
Discipline thesis:degree_discipline
Computer Science, Department of

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Desai, Shounak
Contributors dc:contributor
  • Richard D. Lange

Subjects

dc:subject × 1

Identifiers

dc:identifier.*
Repository record dc:identifier
https://repository.rit.edu/theses/12243

Chain of custody

source
Harvested from
Rochester Institute of Technology
Base URL
repository.rit.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Desai, Shounak. Stochastic Variational Autoencoder. Thesis thesis, https://repository.rit.edu/theses/12243