We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Machine learning models encounter Out-of-Distribution (OoD) errors when the data seen at test time are generated from a different stochastic generator than the one used to generate the training data. One proposal to scale OoD detection to high-dimensional data is to learn a tractable likelihood approximation of the training distribution, and use it to reject unlikely inputs. However, likelihood models on natural data are themselves susceptible to OoD errors, and even assign large likelihoods to samples from other datasets. To mitigate this problem, we propose Generative Ensembles, which robustify density-based OoD detection by way of estimating epistemic uncertainty of the likelihood model. We present a puzzling observation in need of an explanation -- although likelihood measures cannot account for the typical set of a distribution, and therefore should not be suitable on their own for OoD detection, WAIC performs surprisingly well in practice.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1810.01392")
get_code_for_paper("1810.01392")
have("1810.01392")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1810.01392.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1810.01392)
Connect an agent — have() is free.