Proposal Description

Statistical learning continues to evolve as modern data challenges require innovative methodologies capable of handling high dimensionality, heterogeneity, and complex data structures. This session brings together recent advances at the intersection of statistics, machine learning, and data science, with particular emphasis on methods that balance computational efficiency, theoretical soundness, and interpretability. The invited contributions will cover a range of cutting-edge topics, including clustering and classification for large and noisy datasets, scalable methods for dimensionality reduction and visualization, robust and model-based approaches to uncover structure in high-dimensional spaces, and new algorithmic strategies for mixed-type or partially observed data. Applications may span biomedical sciences, finance, social sciences, and beyond, demonstrating how modern statistical learning techniques drive real-world impact. The goal of this session is to highlight recent developments, stimulate discussion between theory and practice, and foster collaboration within the statistical learning community. The session aligns naturally with IASC’s mission to promote computational aspects of statistics and data analysis.