Related papers: Towards Unbiased and Accurate Deferral to Multiple…

Our work revisits the design of mechanisms via the learning-augmented framework. In this model, the algorithm is enhanced with imperfect (machine-learned) information concerning the input, usually referred to as prediction. The goal is to…

Many problems in science and engineering require making predictions based on few observations. To build a robust predictive model, these sparse data may need to be augmented with simulated data, especially when the design space is…

We present a reinforcement learning based framework for human-centered collaborative systems. The framework is proactive and balances the benefits of timely actions with the risk of taking improper actions by minimizing the total time spent…

Sparse modeling for signal processing and machine learning has been at the focus of scientific research for over two decades. Among others, supervised sparsity-aware learning comprises two major paths paved by: a) discriminative methods and…

Detecting machine-generated text (MGT) has emerged as a critical challenge, driven by the rapid advancement of large language models (LLMs) capable of producing highly realistic, human-like content. However, the performance of current…

Classifier models are prevalent in natural language processing (NLP), often with high accuracy. Yet in real world settings, human-in-the-loop systems can foster trust in model outputs and even higher performance. Selective Prediction (SP)…

Both industry and academia have made considerable progress in developing trustworthy and responsible machine learning (ML) systems. While critical concepts like fairness and explainability are often addressed, the safety of systems is…

The Mixture-of-Experts (MoE) architecture is a powerful technique for scaling language models, yet it often suffers from expert homogenization, where experts learn redundant functionalities, thereby limiting MoE's full potential. To address…

Objective: Until now, traditional invasive approaches have been the only means being leveraged to diagnose spinal disorders. Traditional manual diagnostics require a high workload, and diagnostic errors are likely to occur due to the…

Federated learning is a decentralized and privacy-preserving technique that enables multiple clients to collaborate with a server to learn a global model without exposing their private data. However, the presence of statistical…

This paper studies the finite sample performance of the flexible estimation approach of Farrell, Liang, and Misra (2021a), who propose to use deep learning for the estimation of heterogeneous parameters in economic models, in the context of…

Rigorous statistical methods, including parameter estimation with accompanying uncertainties, underpin the validity of scientific discovery, especially in the natural sciences. With increasingly complex data models such as deep learning…

Selecting efficient multi-step synthetic routes is a central challenge in organic synthesis, particularly in medicinal and process chemistry, where route choice directly impacts feasibility, cost, and development efficiency. Data-driven…

NLU models often exploit biases to achieve high dataset-specific performance without properly learning the intended task. Recently proposed debiasing methods are shown to be effective in mitigating this tendency. However, these methods rely…

To plan safe maneuvers and act with foresight, autonomous vehicles must be capable of accurately predicting the uncertain future. In the context of autonomous driving, deep neural networks have been successfully applied to learning…

Deep neural networks trained on biased data often inadvertently learn unintended inference rules, particularly when labels are strongly correlated with biased features. Existing bias mitigation methods typically involve either a)…

The deployment of large-scale models, such as large language models (LLMs) and sophisticated image generation systems, incurs substantial costs due to their computational demands. To mitigate these costs and address challenges related to…

Data-driven fault diagnosis methods often require abundant labeled examples for each fault type. On the contrary, real-world data is often unlabeled and consists of mostly healthy observations and only few samples of faulty conditions. The…

Artificial intelligence (AI) systems accelerate medical workflows and improve diagnostic accuracy in healthcare, serving as second-opinion systems. However, the unpredictability of AI errors poses a significant challenge, particularly in…

In consequential real-world applications, machine learning (ML) based systems are expected to provide fair and non-discriminatory decisions on candidates from groups defined by protected attributes such as gender and race. These…