Convolutional Deep Exponential Families

We describe convolutional deep exponential families (CDEFs) in this paper. CDEFs are built based on deep exponential families, deep probabilistic models that capture the hierarchical dependence between latent variables. CDEFs greatly reduce the number of free parameters by tying the weights of DEFs. Our experiments show that CDEFs are able to uncover time correlations with a small amount of data.

stat.ML cs.LG Gaussian Processes and Bayesian Inference Time Series Analysis and Forecasting Neural Networks and Applications Computer Science Mathematics

View graph Source

Paper

Similar papers

Deep Exponential FamiliesR. Ranganath, Linpeng Tang, Laurent Charlin et al.2014 · International Conference on Artificial Intelligence and Statistics · 158 citations In Library

Building Efficient CNNs Using Depthwise Convolutional Eigen-Filters (DeCEF)Yinan Yu, Samuel Scheidegger, T. McKelvey2019 · Neurocomputing · 3 citations In Library

Building efficient CNNs using Depthwise Convolutional Eigen-Filters (DeCEF)Yinan Yu, Samuel Scheidegger, Tomas McKelvey2024 · Neurocomputing In Library

A CDF-First Framework for Free-Form Density EstimationChen-Hui Song, Mazharul Islam, Lin Wang et al.2026 · 0 citations In Library

DCFNet: Deep Neural Network with Decomposed Convolutional FiltersQiang Qiu, Xiuyuan Cheng, R. Calderbank et al.2018 · International Conference on Machine Learning · 73 citations In Library

Deep equilibrium models as estimators for continuous latent variablesRussell Tsuchida, Cheng Soon Ong2022 · arXiv (Cornell University) · 10 citations In Library

Conjugate Energy-Based ModelsHao Wu, Babak Esmaeili, Michael Wick et al.2021 · arXiv (Cornell University) · 2 citations In Library

Deep Discrete Encoders: Identifiable Deep Generative Models for Rich Data with Discrete Latent LayersSeunghyun Lee, Yuqi Gu2025 · Journal of the American Statistical Association · 4 citations In Library

Sparse Continuous Distributions and Fenchel-Young LossesAndré F. T. Martins, Marcos V. Treviso, António Farinhas et al.2021 · UvA-DARE (University of Amsterdam) In Library

Deep Discrete Encoders: Identifiable Deep Generative Models for Rich Data with Discrete Latent LayersSeunghyun Lee, Yuqi Gu2025 · Journal of the American Statistical Association In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal