|I am an assistant professor in the Department of Computer Science and Department of Mathematics at the National University of Singapore, and an affiliate with the Institute of Data Science. Prior to joining, I was a post-doctoral researcher in LIONS, EPFL, and I completed my PhD at the University of Cambridge.
I am looking for highly motivated PhD students and post-docs to work on algorithmic and theoretical aspects of machine learning and data science. Please see my research and publications pages for further information.
- COM2 #03-46 (Comp. Sci.), S17 #07-01 (Maths)
- +65 6516 1179 (Comp. Sci.), +65 6516 2952 (Maths)
- "scarlett" followed by "@comp.nus.edu.sg"
- (Feb. 2018) Survey monograph pre-print Group Testing: An Information Theory Perspective uploaded. Feedback is welcome!
- (Feb. 2018) Paper Performance of Group Testing Algorithms With Near-Constant Tests-per-Item published in IEEE Transactions on Information Theory
- (Jan. 2019) Paper Support Recovery in the Phase Retrieval Model: Information-Theoretic Fundamental Limits uploaded to arxiv
- (Jan. 2019) Paper Generalized Random Gilbert-Varshamov Codes accepted to IEEE Transactions on Information Theory
- (Dec. 2018) Paper Adversarially Robust Optimization with Gaussian Processes presented as a spotlight talk at NeurIPS 2018
- (Nov. 2018) I have been awarded the National Research Foundation (NRF) Fellowship for the project Robust Statistical Model Under Model Uncertainty
- (Oct. 2018) I have been awarded the NUS Early Career Research Award for the project Information-Theoretic Methods in Data Science
- (Sept. 2018) Paper Noisy Adaptive Group Testing: Bounds and Algorithms accepted to IEEE Transactions on Information Theory
- (Aug. 2018) I have uploaded a tutorial article An Introductory Guide to Fano's Inequality with Applications in Statistical Estimation, to appear in a book titled Information-Theoretic Methods in Data Science (expected 2019 publication)
- (July 2018) Paper Tight Regret Bounds for Bayesian Optimization in One Dimension presented at ICML 2018