Evaluating the performance of machine learning models on diverse and underrepresented
subgroups is essential for ensuring fairness and reliability in real-world applications …

Data-centric AI is an emerging paradigm that emphasizes the critical role of data in real-
world machine learning (ML) systems—as a complement to model development. However …

Data quality is crucial for robust machine learning algorithms, with the recent interest in data-
centric AI emphasizing the importance of training data characterization. However, current …

In this study, we aim to enhance the arithmetic reasoning ability of Large Language Models
(LLMs) through zero-shot prompt optimization. We identify a previously overlooked objective …

Synthetic data serves as an alternative in training machine learning models, particularly
when real-world data is limited or inaccessible. However, ensuring that synthetic data …

Drawing from discussions at the inaugural DMLR workshop at ICML 2023 and meetings
prior, in this report we outline the relevance of community engagement and infrastructure …

Federated learning (FL) is a promising approach for healthcare institutions to train high-
quality medical models collaboratively while protecting sensitive data privacy. However, FL …

Machine Learning (ML) in low-data settings remains an underappreciated yet crucial
problem. This challenge is pronounced in low-to-middle income countries where access to …

Characterizing samples that are difficult to learn from is crucial to developing highly
performant ML models. This has led to numerous Hardness Characterization Methods …

Miscalibration in deep learning refers to there is a discrepancy between the predicted
confidence and performance. This problem usually arises due to the overfitting problem …