Academic:
I am a postdoctoral researcher at Oxford Statistics working with Prof. Patrick Rebeschini. My research focuses on learning theory and high-dimensional statistics, with particular emphasis on heterogeneous data settings. I believe in Slow Science.
I have recently been working on three main problems:
-
Characterising training dynamics of canonical statistical models including shallow neural networks, with a focus on early stopping, benign overfitting, and feature learning
-
Designing algorithms with rigorous guarantees for sequential decision-making problems, including bandits and adaptive inference
-
Uncertainty quantification using distribution-free and assumption-lean methods, including e-values, conformal prediction, and prediction-powered inference
I completed my PhD at Cambridge in 2024, where I was fortunate to be advised by Prof. Ramji Venkataramanan. My PhD work centered on information theory and high-dimensional statistics, motivated by fundamental questions such as: Given a complex statistical estimation problem, what is the minimal amount of data we need to estimate the underlying signal? Can we design efficient, mathematically-principled algorithms that approach the minimum?
Prior to my PhD, I obtained my BA and MEng with distinction in Information and Computer Engineering from Cambridge in 2019.
I was an intern with Microsoft Research Cambridge in 2023, where I worked on error correction codes with ML decoding for Project Silica, a novel glass-based data storage technology. This work has recently appeared in Nature.
Personal:
My first name is pronounced as “Sh-ih-ow Chi” (meaning jade born at dawn in Chinese), but feel free to call me Shirley!
Having lived and worked across four cultures (British, Chinese, Singaporean, and American), I have developed a genuine curiosity about people and a deep appreciation for diverse perspectives. Though introverted by nature, I bring warmth and empathy to the communities I am part of, and I take pride in fostering connections among people through roles such as postgraduate representative.
Besides work, I like practising yoga.
Get in touch:
I am actively seeking collaborators on machine learning theory and statistics. Please send me an email if you are interested in working together! I’m always happy to chat.
Email: shirley.liu [at] stats.ox.ac.uk, xiaoqi.shirley.liu [at] gmail.com