Related papers: Ensuring Robustness in Training Set Based Global 2…
Randomized smoothing is currently a state-of-the-art method to construct a certifiably robust classifier from neural networks against $\ell_2$-adversarial perturbations. Under the paradigm, the robustness of a classifier is aligned with the…
Deep distance metric learning (DDML), which is proposed to learn image similarity metrics in an end-to-end manner based on the convolution neural network, has achieved encouraging results in many computer vision tasks.$L2$-normalization in…
We use the results of previous work building a halo model formalism for the distribution of neutral hydrogen, along with experimental parameters of future radio facilities, to place forecasts on astrophysical and cosmological parameters…
We present measurements of absorption by the 21cm hyperfine transition of neutral hydrogen toward radio sources at substantial look-back times. These data are used in combination with observations of rotational transitions of common…
Goodness-of-fit testing is often criticized for its lack of practical relevance: since ``all models are wrong'', the null hypothesis that the data conform to our model is ultimately always rejected as the sample size grows. Despite this,…
Context. Weak lensing and clustering statistics beyond two-point functions can capture non-Gaussian information about the matter density field, thereby improving the constraints on cosmological parameters relative to the mainstream methods…
Across non-destructive testing (NDT) and structural health monitoring (SHM), accurate knowledge of the systems' reliability for detecting defects, such as Probability of Detection (POD) analysis is essential to enabling widespread adoption.…
We introduce a general framework for testing goodness-of-fit for Gaussian graphical models in both the low- and high-dimensional settings. This framework is based on a novel algorithm for generating exchangeable copies by conditioning on…
The peculiar velocity of the intergalactic gas responsible for the cosmic 21cm background from the epoch of reionization and beyond introduces an anisotropy in the three-dimensional power spectrum of brightness temperature fluctuations.…
This paper proposes a new test for a change point in the mean of high-dimensional data based on the spatial sign and self-normalization. The test is easy to implement with no tuning parameters, robust to heavy-tailedness and theoretically…
A common and natural intuition among software testers is that test cases need to differ if a software system is to be tested properly and its quality ensured. Consequently, much research has gone into formulating distance measures for how…
We present a method for extracting the expected cosmological 21-cm signal from the epoch of reionization, taking into account contaminating radiations and random instrumental noise. The method is based on the maximum a-posteriori…
One of the biggest challenges for applying machine learning to histopathology is weak supervision: whole-slide images have billions of pixels yet often only one global label. The state of the art therefore relies on strongly-supervised…
We present a new non-parametric method to quantify morphologies of galaxies based on a particular family of learning machines called support vector machines. The method, that can be seen as a generalization of the classical CAS…
Due to the broad applications of elliptical models, there is a long line of research on goodness-of-fit tests for empirically validating them. However, the existing literature on this topic is generally confined to low-dimensional settings,…
Neural-network based predictions of event properties in astro-particle physics are getting more and more common. However, in many cases the result is just utilized as a point prediction. Statistical uncertainties, coverage, systematic…
The rotational velocity of distant galaxies, when interpreted as a size (luminosity) indicator, may be used as a tool to select high redshift standard rods (candles) and probe world models and galaxy evolution via the classical angular…
The multi-tracer technique employs a ratio of densities of two differently biased galaxy samples that trace the same underlying matter density field, and was proposed to alleviate the cosmic variance problem. Here we propose a novel…
We investigate structures in the D1 CFHTLS deep field in order to test the method that will be applied to generate homogeneous samples of clusters and groups of galaxies in order to constrain cosmology and detailed physics of groups and…
We address the neural network robustness problem by adding Similarity (i.e., correctly predicted depth-matches into training)-awareness and Distance-to-training-distribution-awareness to the existing output Magnitude (i.e.,…