Kitchen Sink Anomaly Detection
Ranit Das, Marie Hein, Gregor Kasieczka, Michael Kr\"amer, Lukas Lang, Radha Mastandrea, Louis Moureaux, Alexander M\"uck, David Shih

TL;DR
This paper introduces a comprehensive anomaly detection approach using a broad set of observables and new benchmark signals, demonstrating improved sensitivity and reduced training costs.
Contribution
It formulates new simulated signal benchmarks compatible with existing standards and evaluates a highly agnostic observable set called 'kitchen sink' for anomaly detection.
Findings
The 'kitchen sink' approach outperforms baseline sets across various signals.
Attribute bagging reduces training costs with comparable detection performance.
New benchmarks are publicly available for future research.
Abstract
An enormous amount of R&D effort has resulted in many new resonant anomaly detection methods being proposed in recent years. However, the vast majority of previous R&D studies have suffered from two limitations: they have focused on a very small set of simulated signal benchmark models; and they have either used small sets of carefully crafted high-level jet substructure observables, which can be highly performant but are prone to model dependence, or the full collider event phase space, which is more agnostic but suffers from reduced sensitivity. In this work, we address both limitations: we formulate a number of new simulated signal benchmarks, which we make publicly available in a format fully compatible with the LHCO R&D benchmark; and we explore a high-level, yet highly agnostic, observable set consisting of Energy Flow Polynomials in addition to the usual subjettiness variables.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
