Related papers: To Profile or To Marginalize -- A SMEFT Case Study

The subject of features normalization plays an important central role in data representation, characterization, visualization, analysis, comparison, classification, and modeling, as it can substantially influence and be influenced by all of…

Equivariant models leverage prior knowledge on symmetries to improve predictive performance, but misspecified architectural constraints can harm it instead. While work has explored learning or relaxing constraints, selecting among…

We explain a reparameterization invariance in the Standard Model Effective Field Theory present when considering $\bar{\psi} \psi \rightarrow \bar{\psi} \psi$ scatterings (with $\psi$ a fermion) and how this leads to unconstrained…

Numerous Machine Learning (ML) bias-related failures in recent years have led to scrutiny of how companies incorporate aspects of transparency and accountability in their ML lifecycles. Companies have a responsibility to monitor ML…

Complex dynamic systems can be investigated by fitting mechanistic stochastic dynamic models to time series data. In this context, commonly used Monte Carlo inference procedures for model selection and parameter estimation quickly become…

Regularized models are often sensitive to the scales of the features in the data and it has therefore become standard practice to normalize (center and scale) the features before fitting the model. But there are many different ways to…

Regularization is an effective way to promote the generalization performance of machine learning models. In this paper, we focus on label smoothing, a form of output distribution regularization that prevents overfitting of a neural network…

Synchronization phenomena in complex systems are fundamental to understanding collective behavior across disciplines. While classical approaches model such systems by using scalar-weighted networks and simple diffusive couplings, many…

Non-linear mixed effects modeling and simulation (NLME M&S) is evaluated to be used for standardization with longitudinal data in presence of confounders. Standardization is a well-known method in causal inference to correct for confounding…

Polarization, understood as a division into mutually hostile groups, is a common feature of social systems. It is studied in Structural Balance Theory (SBT) in terms of semicycles in signed networks. However, enumerating semicycles is…

Large language models (LLMs) often reflect real-world biases, leading to efforts to mitigate these effects and make the models unbiased. Achieving this goal requires defining clear criteria for an unbiased state, with any deviation from…

Over the past decades, computer-aided diagnosis tools for breast cancer have been developed to enhance screening procedures, yet their clinical adoption remains challenged by data variability and inherent biases. Although foundation models…

Many real applications problems can be encoded easily as quantified formulas in SMT. However, this simplicity comes at the cost of difficulty during solving by SMT solvers. Different strategies and quantifier instantiation techniques have…

The Standard Model Effective Field Theory (SMEFT) provides a powerful theoretical framework for searching for subtle deviations from the Standard Model. In this talk, we present the results from a global fit of the dimension-6 operators of…

We review the status of calculations in the Standard Model Effective Field Theory (SMEFT) beyond leading order (LO). Improving the SMEFT beyond LO allows theoretical errors to be characterized and reduced when considering SMEFT…

We analyze the effects of renormalization group running of the Wilson coefficients in the SMEFT in the context of single Higgs production in association with a top-antitop pair. In particular, we analyze the differential cross section with…

Probabilistic Face Embeddings (PFE) can improve face recognition performance in unconstrained scenarios by integrating data uncertainty into the feature representation. However, existing PFE methods tend to be over-confident in estimating…

The growing deployment of large language models (LLMs) has amplified concerns regarding their inherent biases, raising critical questions about their fairness, safety, and societal impact. However, quantifying LLM bias remains a fundamental…

The proliferation of open-source Large Language Models (LLMs) from various institutions has highlighted the urgent need for comprehensive evaluation methods. However, current evaluation platforms, such as the widely recognized HuggingFace…

Fairness constitutes a concern within machine learning (ML) applications. Currently, there is no study on how disparities in classification complexity between privileged and unprivileged groups could influence the fairness of solutions,…