Related papers: Combining Resonant and Tail-based Anomaly Detectio…
Unsupervised anomaly detection is a challenging task. Autoencoders (AEs) or generative models are often employed to model the data distribution of normal inputs and subsequently identify anomalous, out-of-distribution inputs by high…
A resonance detection scheme and some useful ideas for cavity-based searches of light cold dark matter particles (such as axions) are presented, as an effort to aid in the on-going endeavors in this direction as well as for future…
We propose an outlier robust multivariate time series model which can be used for detecting previously unseen anomalous sounds based on noisy training data. The presented approach doesn't assume the presence of labeled anomalies in the…
This study explores the application of autoencoder-based machine learning techniques for anomaly detection to identify exoplanet atmospheres with unconventional chemical signatures using a low-dimensional data representation. We use the…
Recent unsupervised anomaly detection methods often rely on feature extractors pretrained with auxiliary datasets or on well-crafted anomaly-simulated samples. However, this might limit their adaptability to an increasing set of anomaly…
Wear and tear detection in fleet and shared vehicle systems is a critical challenge, particularly in rental and car-sharing services, where minor damage, such as dents, scratches, and underbody impacts, often goes unnoticed or is detected…
We study the resonant scattering for discrete time quantum walks on graphs with some tails. In our arguments, we reduce the study of resonances to the perturbation of eigenvalues of a finite rank matrix associated with the internal graph.…
State-space models are pivotal for dynamic system analysis but often struggle with outlier data that deviates from Gaussian distributions, frequently exhibiting skewness and heavy tails. This paper introduces a robust extension utilizing…
We present FACADE, a novel probabilistic and geometric framework designed for unsupervised mechanistic anomaly detection in deep neural networks. Its primary goal is advancing the understanding and mitigation of adversarial attacks. FACADE…
Many models beyond the Standard Electroweak Theory, top-down or bottom-up, contain extensions of the gauge symmetry group by extra U(1)' factors which can be understood or treated as subgroups of E(6). A brief overview of such models is…
We propose a tantalizing possibility that misinterpretation of the reconstructed missing momentum may have yielded the observed discrepancies among measurements of the $W$-mass in different collider experiments. We introduce a…
Anomalies in the non-leptonic $\bar{B}^0\rightarrow D^{(*)+}K^{(*)-}$ and $\bar{B}^0_s\rightarrow D^{(*)+}_s\pi^-$ decays may be an indication of physics beyond the Standard Model, but the large deviations require strongly coupled new…
Recently, much progress has been made on techniques to measure the masses of new particles with partially-invisible decays at a hadron collider. We examine for the first time the realistic application of MT2-based measurement methods to a…
We present a family of conditional dual auto-encoders (CoDAEs) for generic and model-independent new physics searches at colliders. New physics signals, which arise from new types of particles and interactions, are considered in our study…
Throughout this thesis, we investigate how effective field theories, combined with unitarization techniques, can be used to explore physics beyond the Standard Model, with particular emphasis on the dynamical origin of electroweak symmetry…
Contrary to what is sometimes stated, the current electroweak precision data easily allow for massive composite resonance states at the natural EW scale, i.e., well over the TeV. The oblique parameters S and T are analyzed by means of an…
Phase retrieval is the classical problem of recovering a signal $x^* \in \mathbb{R}^n$ from its noisy phaseless measurements $y_i = \langle a_i, x^* \rangle^2 + \zeta_i$ (where $\zeta_i$ denotes noise, and $a_i$ is the sensing vector) for…
Anomaly detection is important in many real-life applications. Recently, self-supervised learning has greatly helped deep anomaly detection by recognizing several geometric transformations. However these methods lack finer features, usually…
A sector with QCD-like strong dynamics is common in models of non-standard physics. Such a model could be accessible in LHC searches if both confinement and big-quarks charged under the confining group are at the TeV scale. Big-quark masses…
Learning representations that clearly distinguish between normal and abnormal data is key to the success of anomaly detection. Most of existing anomaly detection algorithms use activation representations from forward propagation while not…