31 August 2026 to 4 September 2026
US/Pacific timezone
All in-person registration fee waivers have now been claimed.

To Chop or Not To Chop: the Question for Variational Autoencoders as Anomaly Detectors in High Energy Physics

Not scheduled
20m

Speaker

Sterre Hoogendoorn (University of Pennsylvania)

Description

Anomaly detection (AD) has recently emerged as an exciting alternative to conventional search strategies in high energy physics. The integration of these techniques into trigger systems is even more recent, but represents a crucial step in expanding the coverage of LHC triggers. In this paper, we explore the direct comparison, as well as combination, of two compression techniques for variational autoencoder (VAE) AD trigger algorithms: (1) utilizing only latent-space derived variables and therefore requiring only half of the VAE (to chop) and (2) applying knowledge distillation (KD) to distill the VAE into a student architecture (not to chop). We demonstrate the feasibility of deploying both techniques on an FPGA within the resource and latency constraints of the LHC trigger environment and further find that a combination of the two leads to the smallest models that maintain, and in some cases, improve, performance with respect to the original VAE architecture.

Do you plan to submit a 4-page extended abstract on OpenReview (only for Presentations/Posters)? No

Authors

Dylan Sheldon Rankin (University of Pennsylvania (US)) Max Michael Cohen (University of Pennsylvania (US)) Rajat Gupta (University of Pittsburgh (US)) Sergey Alexander Scoville (University of Pittsburgh (US)) Sterre Hoogendoorn (University of Pennsylvania) Tae Min Hong (University of Pittsburgh (US))

Presentation materials

There are no materials yet.