all AI news
Free-form Flows: Make Any Architecture a Normalizing Flow
April 25, 2024, 7:43 p.m. | Felix Draxler, Peter Sorrenson, Lea Zimmermann, Armand Rousselot, Ullrich K\"othe
cs.LG updates on arXiv.org arxiv.org
Abstract: Normalizing Flows are generative models that directly maximize the likelihood. Previously, the design of normalizing flows was largely constrained by the need for analytical invertibility. We overcome this constraint by a training procedure that uses an efficient estimator for the gradient of the change of variables formula. This enables any dimension-preserving neural network to serve as a generative model through maximum likelihood training. Our approach allows placing the emphasis on tailoring inductive biases precisely to …
abstract architecture arxiv change cs.lg design estimator flow form free generative generative models gradient likelihood stat.ml training type variables
More from arxiv.org / cs.LG updates on arXiv.org
The Perception-Robustness Tradeoff in Deterministic Image Restoration
2 days, 13 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne