all AI news
Autoregressive Generative Modeling with Noise Conditional Maximum Likelihood Estimation. (arXiv:2210.10715v1 [cs.LG])
Oct. 20, 2022, 1:13 a.m. | Henry Li, Yuval Kluger
stat.ML updates on arXiv.org arxiv.org
We introduce a simple modification to the standard maximum likelihood
estimation (MLE) framework. Rather than maximizing a single unconditional
likelihood of the data under the model, we maximize a family of \textit{noise
conditional} likelihoods consisting of the data perturbed by a continuum of
noise levels. We find that models trained this way are more robust to noise,
obtain higher test likelihoods, and generate higher quality images. They can
also be sampled from via a novel score-based sampling scheme which combats …
arxiv likelihood maximum likelihood estimation modeling noise
More from arxiv.org / stat.ML updates on arXiv.org
Learning linear dynamical systems under convex constraints
1 day, 7 hours ago |
arxiv.org
Inverse Unscented Kalman Filter
2 days, 7 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