Related papers: When Outliers Are Different
Modern neural networks are known to give overconfident prediction for out-of-distribution inputs when deployed in the open world. It is common practice to leverage a surrogate outlier dataset to regularize the model during training, and…
Mendelian Randomisation (MR) uses genetic variants as instrumental variables to infer causal effects of exposures on an outcome. One key assumption of MR is that the genetic variants used as instrumental variables are independent of the…
The variety of gamma-ray burst phenomenology could be largely attributable to differences in the opening angle of an isotropic outflow or to a standard type of event viewed from different orientations. Motivated by this currently popular…
Most of existing outlier detection methods assume that the outlier factors (i.e., outlierness scoring measures) of data entities (e.g., feature values and data objects) are Independent and Identically Distributed (IID). This assumption does…
The Projection Congruent Subset (PCS) Outlyingness is a new index of multivariate outlyingness obtained by considering univariate projections of the data. Like many other outlier detection procedures, PCS searches for a subset which…
It is generally believed that cosmological Gamma Ray Bursts (GRBs) are produced by the deceleration of relativistic objects with Lorentz factor (Gamma) >~ 100. We study the possibility that some GRBs are produced along with relativistic…
The nature of fast radio bursts (FRBs) remains enigmatic. Highly energetic radio pulses of millisecond duration, FRBs are observed with dispersion measures consistent with an extragalactic source. A variety of models have been proposed to…
While robust divergence such as density power divergence and $\gamma$-divergence is helpful for robust statistical inference in the presence of outliers, the tuning parameter that controls the degree of robustness is chosen in a…
Outlier detection is a major topic in robust statistics due to the high practical significance of anomalous observations. Many existing methods are, however, either parametric or cease to perform well when the data is far from linearly…
I present an empirical study of the properties of fast radio bursts (FRBs): Gigahertz-frequency, dispersed pulses of extragalactic origin. I focus my investigation on the sample of seventeen FRBs detected at the Parkes radio telescope with…
In a corpus of data, outliers are either errors: mistakes in the data that are counterproductive, or are unique: informative samples that improve model robustness. Identifying outliers can lead to better datasets by (1) removing noise in…
The optical and X-ray light-curves of long Gamma Ray Bursts (GRBs) often show a complex evolution and in most cases do not track each other. This behaviour can not be easily explained by the simplest standard afterglow models. A possible…
The likelihood ratio test (LRT) and the related $F$ test, do not (even asymptotically) adhere to their nominal $\chi^2$ and $F$ distributions in many statistical tests common in astrophysics, thereby casting many marginal line or source…
Power-law distributions are typical macroscopic features occurring in almost all complex systems observable in nature. As a result, researchers in quantitative analyses must often generate random synthetic variates obeying power-law…
FRB~121102 was the first Fast Radio Burst (FRB) that was shown to repeat. Since its discovery in 2012, more than two hundred bursts have been detected from the source. These bursts exhibit a diverse range of spectral and temporal…
Different questions related with analysis of extreme values and outliers arise frequently in practice. To exclude extremal observations and outliers is not a good decision because they contain important information about the observed…
Soft gamma-ray repeaters (SGR) are a class of high energy transients whose brief emissions are thought to arise from young and highly magnetized neutron stars. The exact cause for these outbursts and the nature of the energy loss remain…
Fast radio bursts (FRBs) are astrophysical transients of still debated origin. So far several hundred events have been detected, mostly at extragalactic distances, and this number is expected to grow significantly over the next years. The…
Outlier detection is an essential capability in safety-critical applications of supervised visual recognition. Most of the existing methods deliver best results by encouraging standard closed-set models to produce low-confidence predictions…
Outlier detection is an important data mining tool that becomes particularly challenging when dealing with nominal data. First and foremost, flagging observations as outlying requires a well-defined notion of nominal outlyingness. This…