Related papers: Data blinding for the nEDM experiment at PSI

Bias is known to be an impediment to fair decisions in many domains such as human resources, the public sector, health care etc. Recently, hope has been expressed that the use of machine learning methods for taking such decisions would…

Neural networks trained on biased datasets tend to inadvertently learn spurious correlations, hindering generalization. We formally prove that (1) samples that exhibit spurious correlations lie on a lower rank manifold relative to the ones…

Phenomenon-specific "adversarial" datasets have been recently designed to perform targeted stress-tests for particular inference types. Recent work (Liu et al., 2019a) proposed that such datasets can be utilized for training NLI and other…

Diffusion Probabilistic Models (DPMs) are powerful generative models that have achieved unparalleled success in a number of generative tasks. In this work, we aim to build inductive biases into the training and sampling of diffusion models…

Neutron scattering is a unique and versatile characterization technique for probing the magnetic structure and dynamics of materials. However, instruments at neutron scattering facilities in the world is limited, and instruments at such…

Prognostics and Health Management ensures the reliability, safety, and efficiency of complex engineered systems by enabling fault detection, anticipating equipment failures, and optimizing maintenance activities throughout an asset…

In order to adhere to regulatory standards governing individual data privacy and safety, machine learning models must systematically eliminate information derived from specific subsets of a user's training data that can no longer be…

The search for a permanent electric dipole moment (EDM) of the muon is an excellent probe for physics beyond the Standard Model of particle physics. We propose the first dedicated muon EDM search employing the frozen-spin technique at the…

State estimation is of considerable significance for the power system operation and control. However, well-designed false data injection attacks can utilize blind spots in conventional residual-based bad data detection methods to manipulate…

The blind application of machine learning runs the risk of amplifying biases present in data. Such a danger is facing us with word embedding, a popular framework to represent text data as vectors which has been used in many machine learning…

NLP models often rely on superficial cues known as dataset biases to achieve impressive performance, and can fail on examples where these biases do not hold. Recent work sought to develop robust, unbiased models by filtering biased examples…

The proliferation of image manipulation for unethical purposes poses significant challenges in social networks. One particularly concerning method is Image Steganography, allowing individuals to hide illegal information in digital images…

The fairness of a deep neural network is strongly affected by dataset bias and spurious correlations, both of which are usually present in modern feature-rich and complex visual datasets. Due to the difficulty and variability of the task,…

Bringing a high-dimensional dataset into science-ready shape is a formidable challenge that often necessitates data compression. Compression has accordingly become a key consideration for contemporary cosmology, affecting public data…

Existing limits on the electric dipole moment (EDM) of the free neutron have provided critical constraints on new sources of CP violation for more than 60 years. A new round of searches are actively underway with the goal of improving the…

Since the initial work by Ashenfelter and Card in 1985, the use of difference-in-differences (DID) study design has become widespread. However, as pointed out in the literature, this popular quasi-experimental design also suffers estimation…

Until now no electric dipole moment of the neutron (nEDM) has been observed. Why it is so vanishingly small, escaping detection for the last 65 years, is not easy to explain. In general it is considered as one of the most sensitive probes…

An efficient monotone data augmentation (MDA) algorithm is proposed for missing data imputation for incomplete multivariate nonnormal data that may contain variables of different types, and are modeled by a sequence of regression models…

A significant impediment to progress in research on bias in machine learning (ML) is the availability of relevant datasets. This situation is unlikely to change much given the sensitivity of such data. For this reason, there is a role for…

Dataset bias is a critical challenge in machine learning since it often leads to a negative impact on a model due to the unintended decision rules captured by spurious correlations. Although existing works often handle this issue based on…