Perfect density models cannot guarantee anomaly detection
Thanks to the tractability of their likelihood, several deep generative models show promise
for seemingly straightforward but important applications like anomaly detection, uncertainty …
for seemingly straightforward but important applications like anomaly detection, uncertainty …
The Roles and Modes of Human Interactions with Automated Machine Learning Systems: A Critical Review and Perspectives
As automated machine learning (AutoML) systems continue to progress in both
sophistication and performance, it becomes important to understand the 'how'and 'why'of …
sophistication and performance, it becomes important to understand the 'how'and 'why'of …
Entropic issues in likelihood-based ood detection
AL Caterini, G Loaiza-Ganem - I (Still) Can't Believe It's Not …, 2022 - proceedings.mlr.press
Deep generative models trained by maximum likelihood remain very popular methods for
reasoning about data probabilistically. However, it has been observed that they can assign …
reasoning about data probabilistically. However, it has been observed that they can assign …
Understanding out-of-distribution: A perspective of data dynamics
Despite machine learning models' success in Natural Language Processing (NLP) tasks,
predictions from these models frequently fail on out-of-distribution (OOD) samples. Prior …
predictions from these models frequently fail on out-of-distribution (OOD) samples. Prior …