Topological obstructions to autoencoding
Open Access
- 29 April 2021
- journal article
- research article
- Published by Springer Nature in Journal of High Energy Physics
- Vol. 2021 (4) , 1-43
Abstract
Autoencoders have been proposed as a powerful tool for model-independent anomaly detection in high-energy physics. The operating principle is that events which do not belong to the space of training data will be reconstructed poorly, thus flagging them as anomalies. We point out that in a variety of examples of interest, the connection between large reconstruction error and anomalies is not so clear. In particular, for data sets with nontrivial topology, there will always be points that erroneously seem anomalous due to global issues. Conversely, neural networks typically have an inductive bias or prior to locally interpolate such that undersampled or rare events may be reconstructed with small error, despite actually being the desired anomalies. Taken together, these facts are in tension with the simple picture of the autoencoder as an anomaly detector. Using a series of illustrative low-dimensional examples, we show explicitly how the intrinsic and extrinsic topology of the dataset affects the behavior of an autoencoder and how this topology is manifested in the latent space representation during training. We ground this analysis in the discussion of a mock “bump hunt” in which the autoencoder fails to identify an anomalous “signal” for reasons tied to the intrinsic topology of n-particle phase space.Keywords
All Related Versions
This publication has 46 references indexed in Scilit:
- Jet flavor classification in high-energy physics with deep neural networksPhysical Review D, 2016
- Jet-images — deep learning editionJournal of High Energy Physics, 2016
- Jet substructure classification in high-energy physics with deep neural networksPhysical Review D, 2016
- Intrinsic dimension estimation: Advances and open problemsInformation Sciences, 2016
- Playing tag with ANN: boosted top identification with pattern recognitionJournal of High Energy Physics, 2015
- Jet-images: computer vision inspired techniques for jet taggingJournal of High Energy Physics, 2015
- A review of novelty detectionSignal Processing, 2014
- Identifying boosted objects with N-subjettinessJournal of High Energy Physics, 2011
- Topology and dataBulletin of the American Mathematical Society, 2009
- On the embeddability of the real projective spacesProceedings of the American Mathematical Society, 1962