Related papers: Computing AIC for black-box models using Generalis…

Determining how to appropriately select the tuning parameter is essential in penalized likelihood methods for high-dimensional data analysis. We examine this problem in the setting of penalized likelihood methods for generalized linear…

Graph Neural Networks (GNNs) are widely used in financial fraud detection due to their excellent ability on handling graph-structured financial data and modeling multilayer connections by aggregating information of neighbors. However, these…

Testing fairness is a major concern in psychometric and educational research. A typical approach for ensuring testing fairness is through differential item functioning (DIF) analysis. DIF arises when a test item functions differently across…

In this paper we present theory and algorithms enabling classes of Artificial Intelligence (AI) systems to continuously and incrementally improve with a-priori quantifiable guarantees - or more specifically remove classification errors -…

The measure of a machine learning algorithm is the difficulty of the tasks it can perform, and sufficiently difficult tasks are critical drivers of strong machine learning models. However, quantifying the generalization difficulty of…

Federated learning (FL) is a distributed training paradigm that enables collaborative learning across clients without sharing local data, thereby preserving privacy. However, the increasing scale and complexity of modern deep models often…

In the realm of statistical learning, the increasing volume of accessible data and increasing model complexity necessitate robust methodologies. This paper explores two branches of robust Bayesian methods in response to this trend. The…

Cross-validation techniques for risk estimation and model selection are widely used in statistics and machine learning. However, the understanding of the theoretical properties of learning via model selection with cross-validation risk…

Symbolic Regression remains an NP-Hard problem, with extensive research focusing on AI models for this task. Transformer models have shown promise in Symbolic Regression, but performance suffers with smaller datasets. We propose applying…

Off-the-shelf Gaussian Process (GP) covariance functions encode smoothness assumptions on the structure of the function to be modeled. To model complex and non-differentiable functions, these smoothness assumptions are often too…

Highly regulated industries, like banking and insurance, ask for transparent decision-making algorithms. At the same time, competitive markets are pushing for the use of complex black box models. We therefore present a procedure to develop…

Generative models can enhance discriminative classifiers by constructing complex feature spaces, thereby improving performance on intricate datasets. Conventional methods typically augment datasets with more detailed feature representations…

To build general-purpose artificial intelligence systems that can deal with unknown variables across unknown domains, we need benchmarks that measure how well these systems perform on tasks they have never seen before. A prerequisite for…

Federated edge learning (FEEL) provides a promising foundation for edge artificial intelligence (AI) by enabling collaborative model training while preserving data privacy. However, limited and heterogeneous local datasets, as well as…

Verifiable training has shown success in creating neural networks that are provably robust to a given amount of noise. However, despite only enforcing a single robustness criterion, its performance scales poorly with dataset complexity. On…

Analog in-memory computing (AIMC) -- a promising approach for energy-efficient acceleration of deep learning workloads -- computes matrix-vector multiplications (MVMs) but only approximately, due to nonidealities that often are…

In the information-based paradigm of inference, model selection is performed by selecting the candidate model with the best estimated predictive performance. The success of this approach depends on the accuracy of the estimate of the…

An accurate assessment of a model's complexity is crucial for topics such as interpretation, generalization, and model selection. However, most existing complexity measures either rely on heuristic assumptions or are computationally…

Fairness AI aims to detect and alleviate bias across the entire AI development life cycle, encompassing data curation, modeling, evaluation, and deployment-a pivotal aspect of ethical AI implementation. Addressing data bias, particularly…

By chaining a sequence of differentiable invertible transformations, normalizing flows (NF) provide an expressive method of posterior approximation, exact density evaluation, and sampling. The trend in normalizing flow literature has been…