E. Puljak: Anomaly Detection with Tensor Networks

Europe/Zurich
42/3-002 (CERN)

42/3-002

CERN

30
Show room on map
Description

https://arxiv.org/abs/2006.02516

Jinhui WangChase RobertsGuifre VidalStefan Leichenauer

Originating from condensed matter physics, tensor networks are compact representations of high-dimensional tensors. In this paper, the prowess of tensor networks is demonstrated on the particular task of one-class anomaly detection. We exploit the memory and computational efficiency of tensor networks to learn a linear transformation over a space with dimension exponential in the number of original features. The linearity of our model enables us to ensure a tight fit around training instances by penalizing the model's global tendency to a predict normality via its Frobenius norm---a task that is infeasible for most deep learning models. Our method outperforms deep and classical algorithms on tabular datasets and produces competitive results on image datasets, despite not exploiting the locality of images.

Videoconference
Zoom Meeting ID
62182982695
Host
Thea Aarrestad
Useful links
Join via phone
Zoom URL
    • 11:00 12:00
      Anomaly Detection with Tensor Networks 1h
      Speaker: Ema Puljak (Universitat Autonoma de Barcelona (ES))