6 papers · 1 filter
NAE, Statistically
Ranit Das, Jonathan Ostertag-Henning, Tilman Plehn +1
Searches for new physics using neural anomaly scores have transformative potential, but suffer from a lack of statistical interpretability. The normalized autoencoder (NAE) provide…
Kitchen Sink Anomaly Detection
Ranit Das, Marie Hein, Gregor Kasieczka +6
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…
SURFing to the Fundamental Limit of Jet Tagging
Ian Pang, Darius A. Faroughy, David Shih +2
Beyond the practical goal of improving search and measurement sensitivity through better jet tagging algorithms, there is a deeper question: what are their upper performance limits…
Generator Based Inference (GBI)
Chi Lung Cheng, Ranit Das, Runze Li +5
Statistical inference in physics is often based on samples from a generator (sometimes referred to as a ``forward model") that emulate experimental data and depend on parameters of…
SIGMA: Single Interpolated Generative Model for Anomalies
Ranit Das, David Shih
A key step in any resonant anomaly detection search is accurate modeling of the background distribution in each signal region. Data-driven methods like CATHODE accomplish this by t…
Accurate and robust methods for direct background estimation in resonant anomaly detection
Ranit Das, Thorben Finke, Marie Hein +4
Resonant anomaly detection methods have great potential for enhancing the sensitivity of traditional bump hunt searches. A key component of these methods is a high quality backgrou…