Related papers: Statistical outliers in random laser emission
We revisit outlier hypothesis testing, propose exponentially consistent low complexity fixed-length and sequential tests and show that our tests achieve better tradeoff between detection performance and computational complexity than…
Three years ago, the report of a solitary radio burst was thought to be the first discovery of a rare, impulsive event of unknown extragalactic origin (Lorimer et al. 2007). The extragalactic interpretation was based on the swept-frequency…
Outlier detection can serve as an extremely important tool for researchers from a wide range of fields. From the sectors of banking and marketing to the social sciences and healthcare sectors, outlier detection techniques are very useful…
Patterns that appear rarely or unusually in the data can be defined as outlier patterns. The basic idea behind detecting outlier patterns is comparison of their relative frequencies with frequent patterns. Their frequencies of appearance…
Extreme wave events or rogue waves (RWs) are both statistically rare and of exceptionally large amplitude. They are observed in many complex systems ranging from oceanic and optical environments to financial models and Bose-Einstein…
Strong anomalous diffusion phenomena are often observed in complex physical and biological systems, which are characterized by the nonlinear spectrum of exponents $q\nu(q)$ by measuring the absolute $q$-th moment $\langle |x|^q\rangle$.…
Many scientific and engineering problems require accurate models of dynamical systems with rare and extreme events. Such problems present a challenging task for data-driven modelling, with many naive machine learning methods failing to…
We study the statistical properties of the combined emission of a population of discrete sources (e.g. X-ray emission of a galaxy due to its X-ray binaries population). Namely, we consider the dependence of their total luminosity…
In previous work, we have predicted novel effects, such as exchange broadening, anomalous scaling of the localization length and a blue shift of the absorption spectrum with increasing disorder strength, for static disorder models described…
This paper studies binary logistic regression for rare events data, or imbalanced data, where the number of events (observations in one class, often called cases) is significantly smaller than the number of nonevents (observations in the…
Complex systems performing spiking dynamics are widespread in Nature. They cover from earthquakes, to neurons, variable stars, social networks, or stock markets. Understanding and characterizing their dynamics is relevant in order to detect…
We analyze the propagation of excitons in a $d$-dimensional lattice with power-law hopping $\propto 1/r^\alpha$ in the presence of dephasing, described by a generalized Haken-Strobl-Reineker model. We show that in the strong dephasing…
Fast radio bursts are extragalactic, sub-millisecond radio impulses of unknown origin [1,2]. Their dispersion measures, which quantify the observed frequency-dependent dispersive delays in terms of free-electron column densities,…
We present the results of numerical simulations of stationary, spherically outflowing, pair winds, with total luminosities of L=10^{35}- 10^{42} ergs/s. These results have direct relevance to the emission from hot, bare, strange stars,…
The anomaly cancellation condition of the Standard Model may be unnatural in theories with extra dimensions as an anomaly of a low-energy 4-dimensional theory can be canceled by an inflow from a bulk. This inflow may give rise to an…
There exist tree-level generalizations of the Type-I and Type-III seesaw mechanisms that realize neutrino mass via low-energy effective operators with d>5. However, these generalizations also give radiative masses that can dominate the…
Universal outlier hypothesis testing is studied in a sequential setting. Multiple observation sequences are collected, a small subset of which are outliers. A sequence is considered an outlier if the observations in that sequence are…
Standard classification theory assumes that the distribution of images in the test and training sets are identical. Unfortunately, real-life scenarios typically feature unseen data (``out-of-distribution data") which is different from data…
We benchmark the robustness of maximum likelihood based uncertainty estimation methods to outliers in training data for regression tasks. Outliers or noisy labels in training data results in degraded performances as well as incorrect…
A dynamical model based on a continuous addition of colored shot noises is presented. The resulting process is colored and non-Gaussian. A general expression for the characteristic function of the process is obtained, which, after a scaling…