Morgane Austern

Morgane Austern is an Assistant Professor of Statistics at Harvard University and an affiliate of the Center of Mathematical Sciences and Applications (CMSA). She holds a PhD in Statistics from Columbia University (2019), where her research focused on limit theorems for dependent/structured data under advisors Peter Orbanz and Arian Maleki. From 2019-2021, she conducted postdoctoral research at Microsoft Research New England. She has been a long-term visitor at the Simons Institute for Theoretical Computing (2022) and was invited to speak at the National Academies of Science, Engineering, and Medicine on AI for mathematical reasoning (2023).

Her research spans

• Probability theory (Stein method, Gaussian universality, concentration inequalities, ergodic theory, optimal transport)
• Machine learning theory (graph neural networks, data augmentation, deep learning theory)
• Statistical inference (resampling methods, causal inference, high-dimensional statistics for dependent data)

Awards

• Kavli Fellow (National Academy of Sciences, 2022)
• NSF CAREER Award (2025)

Her work bridges theoretical foundations across probability, statistics, and machine learning, with a focus on structured data analysis and algorithmic robustness.