Related papers: Binary Discrimination Through Next-to-Leading Orde…

In this paper, we study the problem of learning probabilistic logical rules for inductive and interpretable link prediction. Despite the importance of inductive link prediction, most previous works focused on transductive link prediction…

When random label noise is added to a training dataset, the prediction error of a neural network on a label-noise-free test dataset initially improves during early training but eventually deteriorates, following a U-shaped dependence on…

The production of four bottom quarks is an important benchmark channel for Higgs analyses and searches for new physics at the LHC. We report on the calculation of the next-to-leading order QCD corrections to the process pp -> b anti-b b…

Deep learning has shown remarkable results for image analysis and is expected to aid individual treatment decisions in health care. To achieve this, deep learning methods need to be promoted from the level of mere associations to being able…

Even though convolutional neural networks can classify objects in images very accurately, it is well known that the attention of the network may not always be on the semantically important regions of the scene. It has been observed that…

The production of two b-quark pairs is a prominent background for Higgs and New Physics searches in various extensions of the Standard Model. We present here the next-to-leading order QCD corrections to the quark induced subprocess using…

We present the results of a next-to-leading order calculation of Wt production, including the decays of both the top quark and the W boson. The effects of radiation in the decay of the top quark are also included. The separation of diagrams…

Subliminal learning describes a student language model inheriting a behavioral bias by fine-tuning on seemingly innocuous data generated by a biased teacher model. Prior work has begun to characterize this phenomenon but leaves open…

This work proposes deep network models and learning algorithms for unsupervised and supervised binary hashing. Our novel network design constrains one hidden layer to directly output the binary codes. This addresses a challenging issue in…

The problem of developing binary classifiers from positive and unlabeled data is often encountered in machine learning. A common requirement in this setting is to approximate posterior probabilities of positive and negative classes for a…

We illustrate how the Matrix Element Method at Next-to-Leading Order (MEM@NLO) can be used to discriminate between events arising from the production of a Higgs boson, which subsequently decays to a final state consisting of…

We consider measurement disturbance tradeoffs in quantum machine learning protocols which seek to learn about quantum data. We study the simplest example of a binary classification task, in the unsupervised regime. Specifically, we…

Data driven classification that relies on neural networks is based on optimization criteria that involve some form of distance between the output of the network and the desired label. Using the same mathematical analysis, for a multitude of…

It is well known that cross-sections in perturbative QCD receive large corrections from soft and collinear radiation, whose properties must be resummed to all orders in the coupling. Whether or not the universal properties of this radiation…

Analyses of collider data, often assisted by modern Machine Learning methods, condense a number of observables into a few powerful discriminants for the separation of the targeted signal process from the contributing backgrounds. These…

Making predictions in an unseen environment given data from multiple training environments is a challenging task. We approach this problem from an invariance perspective, focusing on binary classification to shed light on general nonlinear…

Consider the problem where a statistician in a two-node system receives rate-limited information from a transmitter about marginal observations of a memoryless process generated from two possible distributions. Using its own observations,…

In many signal processing applications, including communications, sonar, radar, and localization, a fundamental problem is the detection of a signal of interest in background noise, known as signal detection [1] [2]. A simple version of…

Discriminative linear models are a popular tool in machine learning. These can be generally divided into two types: The first is linear classifiers, such as support vector machines, which are well studied and provide state-of-the-art…

Institutions are increasingly relying on machine learning models to identify and alert on abnormal events, such as fraud, cyber attacks and system failures. These alerts often need to be manually investigated by specialists. Given the…