S15 (2023-2024)

While overparameterization in machine learning models offers great benefits in terms of optimization and generalization, it also leads to increased computational requirements as model sizes grow. In this work, we show that leveraging inherent low-dimensional structure within the model parameter … Read More

While overparameterization in machine learning models offers great benefits in terms of optimization and generalization, it also leads to increased computational requirements as model sizes grow. In this work, we show that leveraging inherent low-dimensional structure within the model parameter … Read More

Clinical documents and textual annotations within electronic health records contain rich information for clinical research and medical practice. Natural Language Processing (NLP) can play an important role in unlocking patient information from clinical narratives. Specifically, the International Classification of Diseases … Read More

Fundamental Sciences and Engineering have been using numerical simulation methods for decades, accelerating the discovery of knowledge and the development of new technologies. At the same time, the Artificial Intelligence and Machine Learning communities were busy developing methods that replicate … Read More

As (large) language models find applications across an increasingly broad spectrum of tasks, the necessity for reliable confidence estimates—or uncertainty quantification (UQ)—on their predictions is critical. However, the selection of appropriate and efficient UQ methods presents a considerable challenge, particularly … Read More

Molecular property prediction is an essential task in drug discovery. Recently, deep neural networks have accelerated the discovery of compounds with improved molecular profiles for effective drug development. In particular, graph neural networks (GNNs) have played a pivotal role in … Read More