all AI news
AdaCat: Adaptive Categorical Discretization for Autoregressive Models. (arXiv:2208.02246v1 [cs.LG])
Aug. 4, 2022, 1:11 a.m. | Qiyang Li, Ajay Jain, Pieter Abbeel
stat.ML updates on arXiv.org arxiv.org
Autoregressive generative models can estimate complex continuous data
distributions, like trajectory rollouts in an RL environment, image
intensities, and audio. Most state-of-the-art models discretize continuous data
into several bins and use categorical distributions over the bins to
approximate the continuous data distribution. The advantage is that the
categorical distribution can easily express multiple modes and are
straightforward to optimize. However, such approximation cannot express sharp
changes in density without using significantly more bins, making it parameter
inefficient. We propose an …
More from arxiv.org / stat.ML updates on arXiv.org
Learning linear dynamical systems under convex constraints
2 days, 5 hours ago |
arxiv.org
Inverse Unscented Kalman Filter
3 days, 5 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