all AI news
Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias. (arXiv:2112.06868v2 [cs.LG] UPDATED)
May 19, 2022, 1:12 a.m. | Frederic Koehler, Viraj Mehta, Chenghui Zhou, Andrej Risteski
cs.LG updates on arXiv.org arxiv.org
Variational Autoencoders are one of the most commonly used generative models,
particularly for image data. A prominent difficulty in training VAEs is data
that is supported on a lower-dimensional manifold. Recent work by Dai and Wipf
(2020) proposes a two-stage training algorithm for VAEs, based on a conjecture
that in standard VAE training the generator will converge to a solution with 0
variance which is correctly supported on the ground truth manifold. They gave
partial support for that conjecture by …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Senior Marketing Data Analyst
@ Amazon.com | Amsterdam, North Holland, NLD
Senior Data Analyst
@ MoneyLion | Kuala Lumpur, Kuala Lumpur, Malaysia
Data Management Specialist - Office of the CDO - Chase- Associate
@ JPMorgan Chase & Co. | LONDON, LONDON, United Kingdom
BI Data Analyst
@ Nedbank | Johannesburg, ZA
Head of Data Science and Artificial Intelligence (m/f/d)
@ Project A Ventures | Munich, Germany
Senior Data Scientist - GenAI
@ Roche | Hyderabad RSS