MLLGOct 27, 2021

Convolutional Deep Exponential Families

arXiv:2110.14800v1
Originality Synthesis-oriented
AI Analysis

This work addresses efficiency in probabilistic modeling for researchers, but it appears incremental as it builds on existing deep exponential families.

The paper tackles the problem of reducing free parameters in deep probabilistic models by introducing convolutional deep exponential families (CDEFs), which tie weights to capture hierarchical dependencies, and experiments show they uncover time correlations with limited data.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes