Bertrand Charpentier, Stephan Ünnemann, Daniel Ügner, Sven Elflein
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.
Several density estimation methods have shown to fail to detect out-of-distribution (OOD) samples by assigning higher likelihoods to anomalous data. Energy-based models (EBMs) are flexible, unnormalized density models which seem to be able to improve upon this failure mode. In this work, we provide an extensive study investigating OOD detection with EBMs trained with different approaches on tabular and image data and find that EBMs do not provide consistent advantages. We hypothesize that EBMs do not learn semantic features despite their discriminative structure similar to Normalizing Flows. To verify this hypotheses, we show that supervision and architectural restrictions improve the OOD detection of EBMs independent of the training approach.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2107.08785")
get_code_for_paper("2107.08785")
have("2107.08785")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2107.08785.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2107.08785)
Connect an agent — have() is free.