Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
Published several papers, such as 'Post-hoc estimators for learning to defer to an expert' (NeurIPS, 2022), 'A statistical perspective on distillation' (ICML, 2021), 'Long-tail learning via logit adjustment' (ICLR, 2021), etc.
Research Experience
Held positions at NICTA, CSIRO Data61, and the Australian National University from 2013 - 2018, working with Bob Williamson and other inimitable colleagues.
Education
Completed honours in Computer Science from the University of Sydney in 2006 under Sanjay Chawla; completed PhD in Computer Science from UC San Diego in 2013 under Charles Elkan.
Background
Research interests: Design and analysis of machine learning algorithms, particularly for (weakly-) supervised learning problems in practice. Current areas of interest include: efficient inference for large (language) models, retrieval and re-ranking, foundations of (weakly-)supervised learning.