Web: http://arxiv.org/abs/1908.01686

Jan. 28, 2022, 2:11 a.m. | Hari Prasanna Das, Pieter Abbeel, Costas J. Spanos

cs.LG updates on arXiv.org arxiv.org

Deep generative modeling using flows has gained popularity owing to the
tractable exact log-likelihood estimation with efficient training and synthesis
process. However, flow models suffer from the challenge of having high
dimensional latent space, the same in dimension as the input space. An
effective solution to the above challenge as proposed by Dinh et al. (2016) is
a multi-scale architecture, which is based on iterative early factorization of
a part of the total dimensions at regular intervals. Prior works on …

architecture arxiv scale

More from arxiv.org / cs.LG updates on arXiv.org

Senior Data Analyst

@ Fanatics Inc | Remote - New York

Data Engineer - Search

@ Cytora | United Kingdom - Remote

Product Manager, Technical - Data Infrastructure and Streaming

@ Nubank | Berlin

Postdoctoral Fellow: ML for autonomous materials discovery

@ Lawrence Berkeley National Lab | Berkeley, CA

Principal Data Scientist

@ Zuora | Remote

Data Engineer

@ Veeva Systems | Pennsylvania - Fort Washington