Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes
Autoencoders and their variants are among the most widely used models in representation learning and generative modeling. However, autoencoder-based models usually assume that the learned representations are i.i.d. and fail to capture the correlations between the data samples. To address this issue, we propose a novel Sparse Gaussian Process Bayesian Autoencoder (SGPBAE) model in which we impose fully Bayesian sparse Gaussian Process priors on the latent space of a Bayesian Autoencoder. We perform posterior estimation for this model via stochastic gradient Hamiltonian Monte Carlo. We evaluate our approach qualitatively and quantitatively on a wide range of representation learning and generative modeling tasks and show that our approach consistently outperforms multiple alternatives relying on Variational Autoencoders.
Code (0)
등록된 구현이 없습니다.
Tasks
Gaussian ProcessesRepresentation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Bayesian autoencoders for data-driven discovery of coordinates, governing equations and fundamental constants
Recent progress in autoencoder-based sparse identification of nonlinear dynamics (SINDy) under $\ell_1$ constraints allows joint discoveries of governing equations and latent coordinate systems from spatio-temporal data,…
Uncertainty QuantificationvalidHierarchical Bayesian Modeling for Clustering Sparse Sequences in the Context of Group Profiling
This paper proposes a hierarchical Bayesian model for clustering sparse sequences.This is a mixture model and does not need the data to be represented by a Gaussian mixture and that gives significant modelling freedom.It…
ClusteringPriors in Bayesian Deep Learning: A Review
While the choice of prior is one of the most critical parts of the Bayesian inference workflow, recent Bayesian deep learning models have often fallen back on vague priors, such as standard Gaussians. In this review, we …
Bayesian InferenceDeep LearningGaussian ProcessesA Bayesian Approach to Sparse plus Low rank Network Identification
We consider the problem of modeling multivariate time series with parsimonious dynamical models which can be represented as sparse dynamic Bayesian networks with few latent nodes. This structure translates into a sparse …
Network IdentificationregressionTime SeriesTime Series AnalysisScalable Robust Bayesian Co-Clustering with Compositional ELBOs
Co-clustering exploits the duality of instances and features to simultaneously uncover meaningful groups in both dimensions, often outperforming traditional clustering in high-dimensional or sparse data settings. Althoug…
Clustering