Related papers: Combining Resonant and Tail-based Anomaly Detectio…
Reconstruction-based methods are a dominant paradigm in time series anomaly detection (TSAD), however, their near-universal reliance on Mean Squared Error (MSE) loss results in statistically flawed reconstruction residuals. This fundamental…
Despite the many empirical successes of QCD, there are a number of intriguing experimental anomalies that have been observed in heavy flavor hadroproduction, in measurements of azimuthal correlations in deep inelastic processes, and in…
Student's $t$ statistic is finding applications today that were never envisaged when it was introduced more than a century ago. Many of these applications rely on properties, for example robustness against heavy tailed sampling…
Conventionally invariant mass or transverse momentum techniques have been used to probe for any formation of some exotic or unusual resonance states in high energy collision. In this work, we have applied symmetry scaling based complex…
Deep Learning (DL) is vulnerable to out-of-distribution and adversarial examples resulting in incorrect outputs. To make DL more robust, several posthoc (or runtime) anomaly detection techniques to detect (and discard) these anomalous…
The production of exotic heavy hadronic particles arise in several models for physics beyond the Standard Model. A study of the detection possibilities of new heavy hadron states with the ATLAS detector is presented. The focus is on…
Detecting orbital anomalies, such as maneuvers, atmospheric decay, and attitude upsets, across the rapidly growing population of low-Earth-orbit (LEO) satellites is a prerequisite for collision avoidance, decay forecasting, and conjunction…
Autoencoder-based anomaly detection methods have been used in identifying anomalous users from large-scale enterprise logs with the assumption that adversarial activities do not follow past habitual patterns. Most existing approaches…
Many searches for physics beyond the Standard Model at the Large Hadron Collider (LHC) rely on top tagging algorithms, which discriminate between boosted hadronic top quarks and the much more common jets initiated by light quarks and…
Datasets with extreme observations and/or heavy-tailed error distributions are commonly encountered and should be analyzed with careful consideration of these features from a statistical perspective. Small deviations from an assumed model,…
In view of the recent diboson resonant excesses reported by both ATLAS and CMS Collaborations, we suggest that a new weak singlet pseudo-scalar particle, $\eta_W$, may decay into two weak bosons while being produced in gluon fusion at the…
Prompt and accurate detection of system anomalies is essential to ensure the reliability of software systems. Unlike manual efforts that exploit all available run-time information, existing approaches usually leverage only a single type of…
Anomaly detection is a significant and hence well-studied problem. However, developing effective anomaly detection methods for complex and high-dimensional data remains a challenge. As Generative Adversarial Networks (GANs) are able to…
Anomaly detection suffered from the lack of anomalies due to the diversity of abnormalities and the difficulties of obtaining large-scale anomaly data. Semi-supervised anomaly detection methods are often used to solely leverage normal data…
Anomaly detection (AD) plays a crucial role in time series applications, primarily because time series data is employed across real-world scenarios. Detecting anomalies poses significant challenges since anomalies take diverse forms making…
Searches for new physics typically rely on proton-proton collisions, where isolated mass bumps are the primary signatures. However, when a new particle is nearly degenerate in mass with a known Standard Model resonance, it can be partially…
With the hyperspectral imaging technology, hyperspectral data provides abundant spectral information and plays a more important role in geological survey, vegetation analysis and military reconnaissance. Different from normal change…
In the real world, long-tailed data distributions are prevalent, making it challenging for models to effectively learn and classify tail classes. However, we discover that in the field of drug chemistry, certain tail classes exhibit higher…
Retrieval of exoplanetary atmospheric properties from their transmission spectra commonly assumes that the errors in the data are Gaussian and independent. However, non-Gaussian noise can occur due to instrumental or stellar systematics and…
In this paper, we propose POTATOES (Partitioning OverfiTting AuTOencoder EnSemble), a new method for unsupervised outlier detection (UOD). More precisely, given any autoencoder for UOD, this technique can be used to improve its accuracy…