High-dimensional probability distributions are important objects in a wide variety of applications.
Generative models provide an excellent manipulation method for training from rich available unlabeled data set and sampling new data points from underlying high-dimensional probability distributions.
The recent proposed Variational auto-encoders (VAE) framework is an efficient high-dimensional inference method to modeling complicated data manifold in an approximate Bayesian way, i.e., variational inference.
We first discuss how to design fast stochastic backpropagation algorithm for the VAE based amortized variational inference method.
Particularly, we propose second order Hessian-free optimization method for Gaussian latent variable models and provide a theoretical justification to the convergence of Monte Carlo estimation in our algorithm.
Then, we apply the amortized variational inference to a dynamic modeling application in flu diffusion task.
Compared with traditional approximate Gibbs sampling algorithm, we make less assumption to the infection rate.
Differing from the maximum likelihood approach of VAE, Generative Adversarial Networks (GAN) is trying to solve the generation problem from a game theoretical way.
From this viewpoint, we design a framework VAE+GAN, by placing a discriminator on top of auto-encoders based model and introducing an extra adversarial loss.
The adversarial training induced by the classification loss is to make the discriminator believe the sample from the generative model is as real as the one from the true dataset.
This trick can practically improve the quality of generation samples, demonstrated on images and text domains with elaborately designed architectures.
Additionally, we validate the importance of generative adversarial loss with the conditional generative model in two biological applications: approximate Turing pattern PDEs generation in synthetic/system biology, and automatic cardiovascular disease detection in medical imaging processing.
","abstract_html":"<p>High-dimensional probability distributions are important objects in a wide variety of applications. </p><p>Generative models provide an excellent manipulation method for training from rich available unlabeled data set and sampling new data points from underlying high-dimensional probability distributions. </p><p>The recent proposed Variational auto-encoders (VAE) framework is an efficient high-dimensional inference method to modeling complicated data manifold in an approximate Bayesian way, i.e., variational inference. </p><p>We first discuss how to design fast stochastic backpropagation algorithm for the VAE based amortized variational inference method. </p><p>Particularly, we propose second order Hessian-free optimization method for Gaussian latent variable models and provide a theoretical justification to the convergence of Monte Carlo estimation in our algorithm. </p><p>Then, we apply the amortized variational inference to a dynamic modeling application in flu diffusion task. </p><p>Compared with traditional approximate Gibbs sampling algorithm, we make less assumption to the infection rate. </p><p>Differing from the maximum likelihood approach of VAE, Generative Adversarial Networks (GAN) is trying to solve the generation problem from a game theoretical way. </p><p>From this viewpoint, we design a framework VAE+GAN, by placing a discriminator on top of auto-encoders based model and introducing an extra adversarial loss. </p><p>The adversarial training induced by the classification loss is to make the discriminator believe the sample from the generative model is as real as the one from the true dataset. </p><p>This trick can practically improve the quality of generation samples, demonstrated on images and text domains with elaborately designed architectures. </p><p>Additionally, we validate the importance of generative adversarial loss with the conditional generative model in two biological applications: approximate Turing pattern PDEs generation in synthetic/system biology, and automatic cardiovascular disease detection in medical imaging processing.</p>","abstract_has_math":false,"creators":["Fan, Kai"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Heller, Katherine"],"committee_chairs":[],"committee_members":[],"year":2017,"date_issued":"2017","date_published":"2017","updated_at":"2026-07-24T02:07:15Z","subjects":["Statistics","Artificial intelligence","Bioinformatics","Adversarial training","Deep Generative Models","Fast inference","Generative adversarial nets","Variational auto-encoders"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10161/16785","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Heller, Katherine"]},{"key":"dc:creator","label":"Author","values":["Fan, Kai"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2018-05-31T21:11:59Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2018-05-31T21:11:59Z"]},{"key":"dc:date.issued","label":"Date","values":["2017"]},{"key":"dc:type","label":"Dc Type","values":["Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Statistics","Artificial intelligence","Bioinformatics","Adversarial training","Deep Generative Models","Fast inference","Generative adversarial nets","Variational auto-encoders"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10161/16785"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["High-dimensional probability distributions are important objects in a wide variety of applications.
Generative models provide an excellent manipulation method for training from rich available unlabeled data set and sampling new data points from underlying high-dimensional probability distributions.
The recent proposed Variational auto-encoders (VAE) framework is an efficient high-dimensional inference method to modeling complicated data manifold in an approximate Bayesian way, i.e., variational inference.
We first discuss how to design fast stochastic backpropagation algorithm for the VAE based amortized variational inference method.
Particularly, we propose second order Hessian-free optimization method for Gaussian latent variable models and provide a theoretical justification to the convergence of Monte Carlo estimation in our algorithm.
Then, we apply the amortized variational inference to a dynamic modeling application in flu diffusion task.
Compared with traditional approximate Gibbs sampling algorithm, we make less assumption to the infection rate.
Differing from the maximum likelihood approach of VAE, Generative Adversarial Networks (GAN) is trying to solve the generation problem from a game theoretical way.
From this viewpoint, we design a framework VAE+GAN, by placing a discriminator on top of auto-encoders based model and introducing an extra adversarial loss.
The adversarial training induced by the classification loss is to make the discriminator believe the sample from the generative model is as real as the one from the true dataset.
This trick can practically improve the quality of generation samples, demonstrated on images and text domains with elaborately designed architectures.
Additionally, we validate the importance of generative adversarial loss with the conditional generative model in two biological applications: approximate Turing pattern PDEs generation in synthetic/system biology, and automatic cardiovascular disease detection in medical imaging processing.
"]},{"key":"dc:title","label":"Title","values":["Deep Generative Models and Biological Applications"]}]}],"canonical_facts":{"dc:contributor.advisor":["Heller, Katherine"],"dc:creator":["Fan, Kai"],"dc:date.accessioned":["2018-05-31T21:11:59Z"],"dc:date.available":["2018-05-31T21:11:59Z"],"dc:date.issued":["2017"],"dc:description.abstract":["High-dimensional probability distributions are important objects in a wide variety of applications.
Generative models provide an excellent manipulation method for training from rich available unlabeled data set and sampling new data points from underlying high-dimensional probability distributions.
The recent proposed Variational auto-encoders (VAE) framework is an efficient high-dimensional inference method to modeling complicated data manifold in an approximate Bayesian way, i.e., variational inference.
We first discuss how to design fast stochastic backpropagation algorithm for the VAE based amortized variational inference method.
Particularly, we propose second order Hessian-free optimization method for Gaussian latent variable models and provide a theoretical justification to the convergence of Monte Carlo estimation in our algorithm.
Then, we apply the amortized variational inference to a dynamic modeling application in flu diffusion task.
Compared with traditional approximate Gibbs sampling algorithm, we make less assumption to the infection rate.
Differing from the maximum likelihood approach of VAE, Generative Adversarial Networks (GAN) is trying to solve the generation problem from a game theoretical way.
From this viewpoint, we design a framework VAE+GAN, by placing a discriminator on top of auto-encoders based model and introducing an extra adversarial loss.
The adversarial training induced by the classification loss is to make the discriminator believe the sample from the generative model is as real as the one from the true dataset.
This trick can practically improve the quality of generation samples, demonstrated on images and text domains with elaborately designed architectures.
Additionally, we validate the importance of generative adversarial loss with the conditional generative model in two biological applications: approximate Turing pattern PDEs generation in synthetic/system biology, and automatic cardiovascular disease detection in medical imaging processing.
"],"dc:identifier.uri":["https://hdl.handle.net/10161/16785"],"dc:subject":["Statistics","Artificial intelligence","Bioinformatics","Adversarial training","Deep Generative Models","Fast inference","Generative adversarial nets","Variational auto-encoders"],"dc:title":["Deep Generative Models and Biological Applications"],"dc:type":["Dissertation"]},"updated_at":"2026-07-24T02:07:15Z"}