Variational autoencoder: Difference between revisions

Revision as of 11:46, 5 October 2024

Revision as of 03:11, 6 October 2024

Line 139:

| issn = 0893-6080

| doi = 10.1016/j.neunet.2021.04.018

| pmid = 33933889

| url = https://www.sciencedirect.com/science/article/pii/S0893608021001556

| arxiv = 1911.13135

}}</ref>

* the [[Maximum Mean Discrepancy]] distance used in the MMD-VAE<ref>{{Cite arxivarXiv|id=1705.02239|title=Maximum Mean Discrepancy Variational Autoencoders|last1=Gretton|first1=A.|last2=Li|first2=Y.|last3=Swersky|first3=K.|last4=Zemel|first4=R.|last5=Turner|first5=R.|date=2017}}</ref>

* the [[Wasserstein distance]] used in the WAEs<ref>{{Cite arxivarXiv|id=1711.01558|title=Wasserstein Auto-Encoders|last1=Tolstikhin|first1=I.|last2=Bousquet|first2=O.|last3=Gelly|first3=S.|last4=Schölkopf|first4=B.|date=2018}}</ref>

* kernel-based distances used in the Kernelized Variational Autoencoder (K-VAE)<ref>{{Cite arxivarXiv|id=1901.02401|title=Kernelized Variational Autoencoders|last1=Louizos|first1=C.|last2=Shi|first2=X.|last3=Swersky|first3=K.|last4=Li|first4=Y.|last5=Welling|first5=M.|date=2019}}</ref>

== See also ==

{{div col|colwidth=22em}}

Line 162 ⟶ 163:

== Further reading ==

* {{cite journal |lastlast1=Kingma |firstfirst1=Diederik P. |last2=Welling |first2=Max |year=2019 |title=An Introduction to Variational Autoencoders |journal=Foundations and Trends in Machine Learning |publisher=Now Publishers |volume=12 |issue=4 |pages=307–392 |doi=10.1561/2200000056 |arxiv=1906.02691 |issn=1935-8237}}

{{Differentiable computing}}