van der Schaar Lab

Research team

Led by Professor Mihaela van der Schaar and based in Cambridge, U.K., the van der Schaar Lab’s research team is one of the most impactful and diverse teams in its field, developing a wide range of ML approaches including deep learning, causal inference, AutoML, time series analysis, ensemble learning, and many more.

The lab’s shared vision is to develop cutting-edge machine learning methods and techniques, with the goal of improving healthcare and medical knowledge.

Prof. van der Schaar

Twitter
LinkedIn
Google Scholar
YouTube
Email

Mihaela van der Schaar

Mihaela van der Schaar is the John Humphrey Plummer Professor of Machine Learning, Artificial Intelligence and Medicine at the University of Cambridge, a Fellow at The Alan Turing Institute in London, and a Chancellor’s Professor at UCLA.

Mihaela has received numerous awards, including the Oon Prize on Preventative Medicine from the University of Cambridge (2018), a National Science Foundation CAREER Award (2004), 3 IBM Faculty Awards, the IBM Exploratory Stream Analytics Innovation Award, the Philips Make a Difference Award and several best paper awards, including the IEEE Darlington Award.

In 2019, she was identified by National Endowment for Science, Technology and the Arts as the most-cited female AI researcher in the UK. She was also elected as a 2019 “Star in Computer Networking and Communications” by N²Women. Her research expertise span signal and image processing, communication networks, network science, multimedia, game theory, distributed systems, machine learning and AI.

Mihaela’s research focus is on machine learning, AI and operations research for healthcare and medicine.

In addition to leading the van der Schaar Lab, Mihaela is founder and director of the Cambridge Centre for AI in Medicine (CCAIM).

Read Mihaela’s full bio.

Postdocs

Twitter
LinkedIn
GitHub
Google Scholar
Email

Fergus Imrie

Fergus Imrie is a postdoc at the ECE Department, University of California, Los Angeles (UCLA).

He is excited and motivated by the promise of transforming healthcare and improving medical knowledge through the use of machine learning in combination with clinical experts.

In particular, Fergus is interested in self-supervised learning and methods for understanding clinical decision making.

Prior to joining the lab, Fergus completed his DPhil (PhD) at the University of Oxford in the Department of Statistics, developing deep learning approaches for drug discovery. Fergus values work with a strong translational impact: his research is currently being used by a number of pharmaceutical companies on active drug discovery projects to develop new therapeutics.

Twitter
LinkedIn
Google Scholar
Email

Zhaozhi Qian

Zhaozhi Qian is a postdoc at the Cambridge Centre for AI in Medicine, the University of Cambridge. 

When he is not grinding code with Copilot or prompting GPT, he enjoys developing new methodologies in generative models and causal inference for the next generation of AI. He is also committed to building open-source software that democratises cutting-edge research and makes AI really Open. 

During his PhD at van der Schaar Lab, Zhaozhi has developed a host of novel algorithms for treatment effect estimation, time series forecasting, and synthetic data generation to address the pressing challenges in healthcare and medicine.  

Prior to joining academia, Zhaozhi worked as a data scientist in one of the largest mobile games companies in the world, designing and implementing AI-powered systems that automatically optimise performance marketing campaigns. He also proudly worked for the NHS as a volunteer during the pandemic, contributing to the UK’s first ICU capacity planning and forecasting system.

PhD students

Twitter
LinkedIn
Google Scholar
Email

Alan Jeffares

Alan Jeffares graduated from University College Dublin with a BSc in Statistics and from University College London with an MSc in Machine Learning. He also spent two years in industry working in applied machine learning.

During his time in industry, Alan helped develop technologies that enabled same day postal delivery for some of the world’s biggest postal services. He and his team presented their work at the World AI Summit in Amsterdam and the Conference of Applied Statisticians Ireland (CASI).

Alan decided to pursue a career in research upon completing his master’s thesis in UCL, which he found to be a rewarding experience. His work during this thesis also resulted in a paper which was published as a spotlight at ICLR 2022.

As a Ph.D. student with the van der Schaar Lab, Alan is delighted to have the opportunity to conduct machine learning research which can contribute towards better healthcare outcomes. As he explains, “I am particularly excited by having the academic freedom to dive into new and exciting areas of machine learning research and further developing these methods towards healthcare applications.”

Twitter
LinkedIn
GitHub
Google Scholar
Email
Personal website

Alex Chan

Alex Chan graduated with a BSc in Statistics at University College London before moving to Cambridge for an MPhil in Machine Learning and Machine Intelligence.

Having started early in research, he won an EPSRC funding grant in his second year of undergraduate for a project on Markov chain Monte Carlo mixing times, and has now had work published at all three of the major machine learning conferences: ICML, ICLR, and NeurIPS.

Much of Alex’s research focuses on understanding and building latent representations of human behavior, with a specific emphasis on understanding clinical decision-making (an important new area of focus for the lab’s research) through imitation, representation learning, and generative modeling. In Alex’s own words, replicating and understanding decision-making at a higher level is, in itself, incredibly interesting, but “also being able to apply it healthcare is hugely important, and promises to actually make a difference to people’s lives in the near future.”

He is particularly interested in developing approximate Bayesian methods to appropriately handle the associated uncertainty that naturally arises in this setting and which is vital to understand.

Drawn to the lab’s special focus on healthcare, Alex notes that “No other area promises the same kind of potential for really having an impact with your research, and the lab benefits from the wide diversity of work being done alongside connections everywhere in both academia and industry.”

Alex’s studentship is sponsored by Microsoft Research.

Outside of machine learning, Alex captains the Wolfson College Boat Club and occasionally keeps up with Krav Maga as a trainee instructor.

Alex has a personal website: alexjchan.com/

Twitter
LinkedIn
GitHub
Google Scholar
Email

Alicia Curth

Alicia Curth, a self-described “full-blooded applied statistician,” recently completed an MSc in Statistical Science at the University of Oxford, where she graduated with distinction and was awarded the Gutiérrez Toscano Prize (awarded to the best-performing MSc candidates in Statistical Science each year). Her previous professional experience includes a data science role for Media Analytics, and a research internship at Pacmed, a healthcare tech start-up.

Alicia also holds a BSc in Econometrics and Operations Research and a BSc in Economics and Business Economics from the Erasmus University Rotterdam.

Since meeting Mihaela van der Schaar at Oxford, Alicia says she’s “been fascinated by the diverse, creative and bleeding edge work of everyone in the lab ever since.”

Alicia hopes to explore ways of making machine learning ready for use in applied statistics, where problems are inferential rather than purely predictive in nature and the ability to give theoretical guarantees is essential. As she sees it, “there is much to gain by replacing linear regression with more flexible machine learning models.” She is particularly excited by potential applications in the areas of personalized and precision medicine, where she hopes machine learning can help healthcare “consider more than just the average patient in the future.”

Alicia is interested in building a better understanding of which algorithms work when and why, and aims to contribute to bridging the gap between theory and practice in machine learning. She is particularly interested in building decision support systems for doctors, and aiding knowledge discovery through next-generation clinical trials as well as analyses of genomics (and other omics) data.

Alicia’s studentship is funded by AstraZeneca.

Alicia has played waterpolo since the age of 12, and was German champion during high school. At Oxford, she represented the university as part of the women’s Blues team.

LinkedIn
Google Scholar
Email

Alihan Hüyük

Alihan is a PhD student in the Department of Applied Mathematics and Theoretical Physics at the University of Cambridge. He is supervised by Professor Mihaela van der Schaar.

Prior to attending Cambridge, he completed a BSc in Electrical and Electronics Engineering at Bilkent University. Alihan’s current research focuses on developing interpretable machine learning methods with the purpose of understanding the decision-making process of clinicians.

Previously, he worked on multi-armed bandit problems in combinatorial and multi-objective settings.

LinkedIn
GitHub
Email

Boris van Breugel

Boris van Breugel is a third-year PhD candidate studying deep generative models and trustworthiness of synthetic data. Before his PhD, Boris completed a MSc in Machine Learning at University College London, for which he received a Young Talent Award by Prins Bernhard Cultuurfonds and a VSBfonds scholarship. Prior to this, he completed a MASt in Applied Mathematics at the University of Cambridge and BSc degrees in Applied Physics and Applied Mathematics at Delft University of Technology.

While studying for his MSc in Machine Learning at UCL, Boris developed a model to detect Alzheimer’s disease using MRI and PET scans, enabling diagnosis at an earlier stage and thereby aiding the development of more effective treatment plans. He found the healthcare domain uniquely challenging and rewarding, and decided to continue research in the domain.

As a PhD student with the van der Schaar Lab, he works on the intersection of synthetic data and trustworthy AI. He says, “Synthetic data promises a future where data is more widely available and where data is tailored to individual needs. At the same time, there are many challenges for creating this data, and ensuring downstream results are trustworthy.”

Previous work has focussed on privacy, fairness, distributional shifts, uncertainty, and evaluation of synthetic data, which he has presented at major ML conferences (NeurIPS, ICML, AISTATS).

Boris’ studentship is funded by the Office of Naval Research (ONR).

Google Scholar
Email

Hao Sun

Hao received his B.Sc. in Physics from Peking University, and M.Phil. from the Chinese University of Hong Kong’s Multimedia Lab (MMLab).

His M.Phil. research focused on sample-efficient deep reinforcement learning (DRL) algorithms for continuous control. He proposed several sample-efficient algorithms for sparse reward goal-conditioned tasks, general continuous control locomotion tasks, diversity-seeking exploration and safe reinforcement learning tasks.

Hao’s previous work on self-supervised sample-efficient reinforcement learning algorithms has already been featured in spotlight presentation at NeurIPS 2019. As Hao points out, “the area of supervised-learning based RL is thriving nowadays, and is definitely a promising under-explored direction worthy of further investigation!”

Although DRL has achieved great success in computer games and similar applications, deploying prevailing DRL algorithms in real-world applications is still an open question. In his own words, Hao believes that “we should be able to take DRL beyond simply working in simulations; the lab is in a unique position to apply it in real-world scenarios where we can help people making better decisions.”

Hao believes that healthcare provides a natural scenario where high-quality decision-making policy is needed, but that there is still a pressing need to address the interpretability, transparency, and reliability issues of modern reinforcement learning and inverse reinforcement learning algorithms.

Hao’s research is supported by funding from the Office of Naval Research (ONR).

Twitter
Google Scholar
Email

Jeroen Berrevoets

Jeroen Berrevoets joined the van der Schaar Lab from the Vrije Universiteit Brussel (VUB). Prior to this, he analyzed traffic data at 4 of Belgium’s largest media outlets and performed structural dynamics analysis at BMW Group in Munich.

As a PhD student in the van der Schaar Lab, Jeroen plans to explore the potential of machine learning in aiding medical discovery, rather than simply applying it to non-obvious predictions. His main research interests involve using machine learning and causal inference to gain understanding of various diseases and medications.

Much of this draws from his firmly-held belief that, “while learning to predict, machine learning models captivate some of the underlying dynamics and structure of the problem. Exposing this structure in fields such as medicine, could prove groundbreaking for disease understanding, and consequentially drug discovery.”

Jeroen’s studentship is supported under the W. D. Armstrong Trust Fund. He will be supervised jointly by Mihaela van der Schaar and Dr. Eoin McKinney.

LinkedIn
GitHub
Google Scholar
Email
Personal website

Jonathan Crabbé

Jonathan Crabbé’s academic passions range from black boxes to black holes. He joins the lab following a MASt in in theoretical physics and applied mathematics at Cambridge, which he passed with distinction, receiving the Wolfson College Jennings Price. Before this, he received an M.Sc. from Ecole Normale Superieure of Paris’ Department of Physics, with his studies fully funded under the LABEX-ICFP Scholarship (awarded based on academic excellence).

Jonathan’s work focuses on the development of explainable artificial intelligence (XAI), which he believes to be one of the biggest challenges in machine learning. Through his research over the coming years, he hopes to help deploy of state-of-the-art machine learning models, meeting the expectations of (possibly non-expert) users by supplementing the predictions made by models with informative and actionable explanations.

Jonathan describes explainability as “crucial in numerous domains of application, such as healthcare, where life-impacting decisions might be taken based on machine learning models.” He points out that “the impact of XAI goes well beyond state-of-the-art methods, as progress in machine learning will need to be based on a better understanding of model’s architecture.”

Jonathan’s studentship is supported by funding from Aviva.

In his time off, Jonathan enjoys hiking, swimming, diving and crafting cocktails for his friends.

LinkedIn
GitHub
Email

Krzysztof Kacprzyk

Krzysztof graduated with an M.Sc. in Mathematical Sciences at the University of Oxford, where he studied statistics, geometry and quantum computing. His dissertation was devoted to optimization algorithms for the generalized multi-armed bandit problem. Before moving to Oxford, he completed his B.Sc. in Mathematics at University College London.

In his second year of undergraduate study, Krzysztof was awarded funding from EPSRC to conduct research in mathematical modelling, during which he designed a biomechanical model for rice seedling emergence. Later, as an Oxford AI Society member, he investigated bias, fairness and privacy issues in computer vision algorithms and presented his findings at the ICLR workshop on Synthetic Data Generation.

Krzysztof is driven to explore ways for machine learning to aid scientific discovery, especially in pharmacology. He is particularly interested in combining data from clinical trials with data from electronic health records to suggest better treatments for patients.

In his leisure time, Krzysztof enjoys playing the piano, building robots, juggling and performing yo-yo tricks.

Krzysztof’s research is supported by funding from Roche.

Twitter
LinkedIn
GitHub
Google Scholar
Email

Nabeel Seedat

Before joining the van der Schaar Lab, Nabeel received a merit scholarship for a master’s degree at Cornell University, researching Bayesian deep learning and uncertainty estimation for high stakes applications. In addition, he holds a master’s degree from the University of the Witwatersrand (South Africa), where he was awarded a National Research Foundation grant for his work applying signal processing and machine learning to Parkinson’s disease diagnostics in low-resource settings.

Professionally, Nabeel has worked as a machine learning engineer in the United States and South Africa. The computer vision and natural language processing models he worked on are currently deployed and serving millions of customers on a daily basis.

Nabeel is keenly aware that taking methods from the lab to the bedside “requires a unique focus beyond just high-performance predictive models; it requires the development of a toolkit of methods for transfer learning across domains and locations, learning on smaller datasets, understanding model biases and quantifying model reliability and uncertainty are fundamentally needed to bridge this divide.”

Nabeel’s research is supported by funding from the Cystic Fibrosis Trust.

Twitter
LinkedIn
GitHub
Google Scholar
Email

Nicolás Astorga

Nicolás graduated from the University of Chile with a BSc in Electrical Engineering, Mechanical Engineering, and Computer Science as well as a MSc in Computer Science and Electrical Engineering from the same institution.

Previously, Nicolás specialised in variational and information-theoretic research, making notable contributions such as “Matching priors and conditional for clustering” (ECCV2020) during his Harvard University internship. Professionally, he deployed Machine Learning models at ALeRCE, primarily focusing on classifying time series and tabular data for astronomical discoveries. Now, fuelled by his passion, Nicolás joins the Van der Schaar Lab to advance ML in medical research.

As a PhD student, he intends to explore various aspects of uncertainty quantification in ML. He is impressed by how uncertainty naturally appears in many ML formulations, e.g., as exogenous noise in Structural Causal Models or as epistemic uncertainty in Active Learning methods. He is convinced that uncertainty quantification is fundamental for creating more general artificial intelligence methods that, at the same time, can be used in real-world applications.

When Nicolás is not doing research, he enjoys playing video games or playing guitar.

W.D. Armstrong Trust Fund and Cystic Fibrosis Fund fund Nicolás’s research.

GitHub
Email

Nicolas Huynh

PhD student – joined the lab in 2022

Nicolas joins us freshly graduated with a Diplôme d’Ingénieur from Ecole Polytechnique (France) and an MSc in Machine Learning from Ecole Normale Supérieure Paris-Saclay.

During his studies, Nicolas focussed on a wide array of ML topics, such as cost-aware Bayesian optimisation, reward learning, and combining natural language processing with graphs.

Equipped with experience in a broad range of topics and a cemented passion for his field of research, Nicolas is excited to join the van der Schaar lab. In his words, “the exceptional combination of brilliant minds making up the lab, the immense impact of the lab’s research, and its expositions” make the lab the ideal place to pursue a meaningful PhD.

For his PhD, Nicolas aspires to work on various topics such as representation learning, causality, and data-centric ML to further translate their huge potential into the challenging domain of healthcare.

When he is not working on his research, he enjoys watching and playing football with friends, be it on the pitch or with a controller in his hands.

Nicolas’ research is supported by funding from Illumina.

Twitter
LinkedIn
Google Scholar
Email

Paulius Rauba

PhD student – joined the lab in 2022

Paulius’ path to the van der Schaar Lab is a particularly interesting one.

Although he only recently graduated as Shirley Scholar with an MSc in Social Data Science from Oxford University, he comes with years of work experience at the intersection of academia, business, and international organisations.

Paulius has previously worked very practically as an AI expert for the European Commission and the National Education Agency in Lithuania, evaluating proposals on the implementation of AI and advising on how to best build robust AI systems.

However, he also gathered experience in teaching as visiting lecturer at ISM University, instructing on econometrics and statistical learning, and as a lecturer at private coding academies introducing newcomers to Python for data science and statistics. 

While working as a data scientist in a large corporate bank, Paulius acquired further know-how by building end-to-end data science and machine learning pipelines, implementing causal inference models, and developing propensity models. Before that, he worked as a data analyst in a company offering big data predictive analytics solutions and as an analyst in a management consulting firm. 

Paulius joins us for his Ph.D. hoping to contribute his statistical and deep learning knowledge and to help build a new generation of causal deep learning tools to transparently and quantifiably solve practical problems faced by clinicians. 

During his free time, you might find Paulius scuba diving with manta rays, snowboarding, kitesurfing, jogging, playing tennis, or (occasionally) running from orangutans in the jungle.

Paulius’ research is supported by funding from AstraZeneca.

Twitter
GitHub
Personal website
Email

Qiyao Wei

PhD student – joined the lab in 2023

Qiyao Wei graduated from University of Toronto with a BSc in Computer Engineering before joining the van der Schaar lab. Now, he is a PhD student in the Department of Applied Mathematics and Theoretical Physics.

He is excited about the huge potential machine learning carries. On the theoretical side, he believes improvements to machine learning methods should come from a principled and analytical angle. On the empirical side, he is also keen on using machine learning to transform healthcare and medicine in combination with clinical experts.

In particular, Qiyao works at the intersection of deep learning and dynamical systems, with the research of Neural Ordinary Differential Equations as a prime example. He also aims to apply machine learning to improve clinical treatment decisions in a healthcare setting.

Besides research, Qiyao enjoys playing tennis, swimming, and cycling.

Qiyao’s studentship is gracefully sponsored by the Cambridge Center for AI in Medicine and GSK. 

Twitter
LinkedIn
GitHub
Google Scholar
Email

Sam Holt

Sam holds a M.Eng. in Engineering Science from the University of Oxford, where he graduated with a first-class degree and numerous awards for academic excellence (placing 2nd in the year for his master’s thesis).

In the course of his studies, Sam undertook two machine learning research internships at the University of Oxford: one researching detecting and tracking cars in noisy radar data (for a self-driving car), and the other in economic time-series forecasting. He also initiated his own original research into noise reduction on propellers, developing a propeller design that emits 44% less noise.

Upon graduating, Sam worked for an Oxford spin out, Mind Foundry, investigating dialogue systems for an industrial client. He has also authored and taught an online machine learning course covering recent work, and shared his passion for machine learning through teaching students in a classroom at a London-based tech-MBA program. Previously, he has collaborated and led three quantitative financial research projects, alongside working in data science and software engineering for a quantitative finance startup, Fifth Row Technologies. He has also created proof-of-concept automation ML tools to help doctors in GP practices.

Sam’s research is supported by funding from AstraZeneca.

LinkedIn
GitHub
Google Scholar
Email
Personal website

Kasia Kobalczyk

Kasia joined our lab after completing her MASt in Mathematical Statistics (Part III) at the University of Cambridge. Prior to this, she earned her BSc in Mathematics and Statistics from the University of Warwick, where she was recognised for her top-of-class performance and outstanding results in mathematics-oriented subjects with the Warwick Statistics Prize and the Institute of Mathematics and its Applications (IMA) Prize.

During her bachelors, Kasia cultivated her passion for machine learning and statistics by coordinating and engaging in multiple research projects as the Research and Education Lead of Warwick Data Science Society. In her second year of undergraduate, she received a research grant to study Graphical Models, leading to her first publication in a scientific journal. Kasia has also gained a comprehensive professional experience through several internships in data science and quantitative research roles.

Equipped with the blend of academic and practical experiences, Kasia is eager to contribute to the research endeavours at the van der Schaar Lab. She is especially keen to work on data- and reality-centric AI. Her research is dedicated to understanding the process of knowledge acquisition, belief formation, and human decision-making, ultimately contributing to the advancement of personalised education and healthcare. She aspires to develop AI models that empower individuals’ creativity, thus fostering innovation. Within her research pursuits, Kasia particularly enjoys working with Bayesian methods, imitation and representation learning.

Kasia’s studentship is sponsored by Eedi, where she collaborates with industry experts to enhance the effectiveness of studying and teaching mathematics among school-age children. This involves the development of novel machine learning models aimed at understanding students’ misconceptions and guiding their learning paths.

LinkedIn
GitHub
Google Scholar
Personal website

Tennison Liu

PhD student – joined the lab in 2021

Tennison is a Ph.D. student in the Cambridge Centre for AI in Medicine as well as the van der Schaar Lab.

Tennison graduated from the University of Sydney with a B.Eng in Electrical Engineering, receiving the University Medal (highest mark), and then continued to an M.Phil. in Machine Learning and Machine Intelligence at the University of Cambridge, where he first worked with Prof. van der Schaar and was awarded the John CB Chau Prize for highest M.Phil. mark.

Tennison has held research data scientist roles at Cochlear, IBM, and Macquarie Group in Australia, but felt drawn to the intellectual stimulation of machine learning research. In his own words, he opted to join the lab for its “great resources that are rarely found in other institutions, in terms of research collaborations, faculty, and brilliant students.”

Tennison currently expects his work with the van der Schaar lab and the Cambridge Centre for AI in Medicine to focus on areas such as synthetic data, discovery using machine learning, and deep self-supervision.

In his spare time, Tennison enjoys rowing with the St Edmund’s College Boat Club, playing basketball, and working out in the gym. He also enjoys photography and (in the right mood) will play the piano and trumpet.

Tennison’s research is supported by funding from AstraZeneca.

Twitter
LinkedIn
Email

Yangming Li

PhD student – joined the lab in 2022

Yangming comes to us with the practical experience he gathered working as a researcher at Tencent AI Lab, focussing on natural language processing (NLP). During his time in the industry, he participated in developing a spoken dialogue system for the Alibaba Group supporting oral and real-time negotiations with human debtors. Other projects included abstracting engineering challenges into research problems and working on solving them.

Yangming left Tencent with a number of publications at impactful conferences like ACL and ICLR under his belt.

Previously, he graduated with a bachelor’s degree in computer science from Harbin Institute of Technology.

Now, Yangming is joining the van der Schaar lab with a great interest in our vision for ML for healthcare. His future research will focus on time-series modelling, representation learning, and neural differential equations.

Twitter
LinkedIn
Email

Max Ruiz Luyten

PhD student – joined the lab in 2023

Max graduated from the Interdisciplinary Higher Education Centre at the Polytechnic University of Catalonia with a Bachelor’s degree in Mathematics and another in Physics Engineering. He was a graduate visiting student in AI at MIT, and his work resulted in a publication in Nature Communications that was highlighted in the Editors’ Highlights webpage of recent research for “Applied Physics and Mathematics,” which showcases the 50 best papers recently published in an area.

He then worked at Meta in Instagram’s recommender systems before joining the van der Schaar Lab. In his own words, he was drawn by the “impact-centered culture in the group and our common interest in seeking the breakthroughs that currently separate ML and unsolved societal problems, commonplace in healthcare.” He feels that in academic research, it is “unfortunately too easy to detach from the test of reality,” which he wants to avoid and was a critical factor in choosing the van der Schaar lab with its reality-centric agenda.

Max aims to tackle temporal control tasks effectively by integrating multiple domain data while handling different resolution scales and uncertainty. This would apply to help clinicians effectively provide personalised medicine from a holistic view of the patient’s history but would also support economic or environmental policies, traffic control, and many other critical tasks. He thus seeks to focus his research around the components needed to that end, from modelling and learning the system’s structure to control-like strategies such as RL.

Max’ work is funded by AstraZeneca

LinkedIn
GitHub
Email

Julianna Piskorz

PhD student – joined the lab in 2023

Julianna is a graduate of the BSc in Mathematics and Statistics at Imperial College London. Her desire to study the foundations of Machine Learning motivated her to undertake the MSc in Statistical Science course at the University of Oxford, which she has recently completed. In her Master Thesis, supervised by Prof. Patrick Rebeschini, she explored and compared different supervised learning methods derived from the infinite-width limits of neural networks.

Prior to joining the lab, Julianna has also completed an internship at Apple, during which she designed a solution which combined large volumes of diverse data from across different systems and departments to provide the Search Engine Optimisation team with smart and informed insights. She has also worked with a Venture Capital startup to create a tool allowing to calculate the similarity in the investing patterns and the dependencies between different VC firms, and visualise these in a clear and informative way.

Julianna’s studentship is founded by Astra Zeneca.

Email

Yuchao Qin

Yuchao Qin joined the van der Schaar Lab from Tsinghua University, where he received an BS in Automation and MS in Control Science and Engineering.

In 2019, Yuchao won 1st prize in the Oral Presentation category of the Beijing University Artificial Intelligence Academic Forum. He was awarded a highly competitive national scholarship in same year, while pursuing his master’s degree.

Yuchao’s prior research primarily focused on control and optimization methods for smart power systems with joint utilization of control theory and machine learning techniques. He has published a number of papers at leading conferences and in journals in intelligent power and energy systems.

His recent research interests are reinforcement learning, and inverse reinforcement learning. He explains that during the course of his research at Tsinghua he learned that “there’s a strong connection between optimal control theory and reinforcement learning,” and that “reinforcement learning is definitely one of the most promising methods to achieve higher level artificial intelligence as it allows machine to learn itself via interacting with the environment.” He believes that these techniques will ultimately contribute to the intelligence revolution in healthcare.

Yuchao describes the van der Schaar Lab as “one of the world’s leading labs in the field of machine learning, including reinforcement learning,” and hopes to use his studentship to “further explore the possibility of reinforcement learning methods, and their applications in understanding decision-making strategies of clinicians and other healthcare professionals.”

Yuchao’s studentship is funded by the U.K. Cystic Fibrosis Trust.

Associates

LinkedIn

Andrew Rashbass

Joined with us in 2023

Andrew Rashbass is the former CEO of The Economist Group, Reuters and Euromoney Institutional Investor PLC, and now works closely with Mihaela and the van der Schaar Lab on a  range of initiatives.

LinkedIn
Podcast
Email

Tim Schubert

Joined with us in 2023

Tim Schubert studies medicine in the MD/PhD track at Heidelberg University. 


He is fascinated by complex systems and efforts to understand them from an interdisciplinary perspective.

Within the realm of neurogenetics research at the Institute of Human Genetics, Tim focuses on unraveling the complexities of rare neurodevelopmental disorders. His work sheds light on how genetic changes impact human cognition and behaviour, with a particular focus on the prosocial peptide oxytocin.

Moreover, Tim is excited about harnessing the power of cutting-edge machine learning methods for solving medical challenges. He believes that finding common vocabulary is one of the keys towards bridging healthcare and AI. Tim works with the van der Schaar Lab on numerous initiatives, with a particular interest in quantitative epistemology, early diagnosis and synthetic data.

Outside the lab, Tim channels his creativity into producing an educational podcast for medical students. Besides his academic endeavours, he finds immense joy in cooking up elaborate dinners with friends, gliding across (and sometimes falling into) rivers on rowing boats, exploring new horizons through travel, and composing some musical hiccups on his piano.

Tim is supported by a scholarship of the German Academic Scholarship Foundation (Studienstiftung des deutschen Volkes).

LinkedIn
Email

Tim Oosterlinck

Joined with us in 2023

Tim Oosterlinck, nearing the completion of his Master’s in Medicine at KU Leuven, has always been intrigued by technology, a spark ignited during his childhood by watching his father build computers. He’s keen on melding the worlds of medicine and technology to find innovative solutions to address current and future healthcare challenges.

This curiosity led him to delve into AI-driven medicine, starting with a bachelor paper on machine learning for predicting hepatic arterial thrombosis post-liver transplantation. His admittance into the Honours program at KU Leuven further propelled his research endeavours.

At KU Leuven, Tim’s current projects revolve around the integration of Augmented Reality in surgical procedures, with an emphasis on perioperative navigation, 3D printing, and AR software development. He’s also a member of the Surgical AI Research Team at Orsi Academy, an institution specializing in robotic surgery training. There, he’s working on advanced computer vision methodologies to refine the surgical operations, and elevating surgeon training by providing objective metrics to evaluate their proficiency.

At the van der Schaar Lab, Tim is currently focused on ML-powered risk prediction models, working with Large Language Models and challenging existing healthcare paradigms.

Outside academia, he enjoys spending time with friends, long-distance running, surfing, snowboarding, and skiing.

Research engineers

Twitter
LinkedIn
GitHub
Google Scholar
Email
Personal website

Evgeny Saveliev

Research engineer & part-time Ph.D. student – joined the lab in 2020

Evgeny is one of the lab’s research engineers, and has been a part-time Ph.D. student since 2021. His educational background is Natural Sciences at the University of Cambridge, followed by postgraduate study in Computer Science at University of Southampton.

Evgeny was an AI Resident at Microsoft Research Cambridge before joining the lab, where he worked on projects covering meta-learning and reinforcement learning as applied to recommender systems. He also has experience in computational finance, having worked in a fintech start-up and commodities trading.

Evgeny facilitates turning the lab’s research code into robust production quality code, making it more scalable, applying software engineering best practices; he also collaborates with our PhD students on some research topics.

He is particularly interested in working on AutoML and time-series modelling, as well as machine learning for time series, and synthetic data.

Rob Davis
Twitter
LinkedIn
GitHub
Email

Rob Davis

Research engineer – joined in 2022

Rob is one of our research engineers since joining in 2022. His educational background is Physical Natural Sciences at the University of Cambridge.

Rob worked for five years at a medical software company before joining us. In his roles of Senior Data Scientist and Data Engineer, he focussed on data extraction from scientific literature, and it was here he became excited by applying Machine Learning methods in medical contexts.

Rob works to make research code robust, ensuring software engineering best practices are applied. He also creates user interfaces that demonstrate the research methods to make sure that their power can be understood by as many people as possible.

He has so far shown a great interest in the interpretability of Machine Learning methods.

Operations

Sally Po Tsai
Twitter
LinkedIn
Email

Sally Po Tsai

PA / Administrator – joined the lab 2022

Sally supports Professor Mihaela van der Schaar and her research group, based at the Department of Applied Mathematics and Theoretical Physics, at the Centre for Mathematical Sciences.

Sally studied Education (PhD) at the University of Cambridge, graduating in 2020. Sally previously worked as a research assistant on different projects at the University of Cambridge (2020-2022).

Recent alumni

LinkedIn
Google Scholar
Email
Cambridge Uni. page

Dan Jarrett

Dan graduated from Princeton University with a B.A. in economics, and from Oxford with an MSc. in computer science.

He has professional experience in finance, consulting, and technology spaces, and research interests include representation learning and decision-making over time.

His PhD thesis was titled “Advances in Reinforcement Learning for Decision Support”. In July 2023, Dan has successfully passed his PhD viva.

He is now working as a Research Scientist at DeepMind.

Twitter
LinkedIn
GitHub
Google Scholar
Email

Ioana Bica

2018 – 2022 PhD

Ioana Bica joined the lab as PhD student at the University of Oxford and at the Alan Turing Institute in 2018. She had previously completed a BA and MPhil in Computer Science at the University of Cambridge where she specialised in machine learning and its applications to biomedicine.

Ioana’s PhD research focused on building machine learning methods for causal inference and individualised treatment effect estimation from observational data. In particular, she has developed methods capable of estimating the heterogeneous effects of time-dependent treatments, thus enabling us to determine when to give treatments to patients and how to select among multiple treatments over time. Her PhD thesis was titled “Causal Inference Methods for Supporting, Understanding, and Improving Decision-Making.” In July 2022, Ioana has successfully passed her PhD viva.

Recently, Ioana has started working at DeepMind in London as a Research Scientist.

LinkedIn
Google Scholar
Email

Yao Zhang

2019 – 2022 PhD

Yao Zhang joined the lab as PhD student in 2019. His PhD research has focused on conditional causal inference, answering questions about personalised treatment effects, and about handling complex experimental designs.

All of this work has culminated in Yao’s Ph.D. thesis, entitled “Topics in conditional causal inference.” Yao was awarded his doctorate by the Department of Applied Mathematics and Theoretical Physics at the University of Cambridge.

Prior to this, he studied Mathematics, Statistics and Machine Learning (BA and MPhil Hons.) at the University of Cambridge and the University of Birmingham.

Yao is now a Postdoctoral Researcher at Stanford University.

His primary research interest is Causal Inference.

Twitter
LinkedIn
Google Scholar

Ahmed Alaa

2015-2019 (Ph.D); 2019-2021 (postdoc)

Ahmed joined the van der Schaar Lab as a Ph.D. student in 2015 at the University of California, Los Angeles, and completed his doctoral research (supervised by Mihaela van der Schaar) in December 2019. His dissertation, entitled “Discovering Data-Driven Actionable Intelligence for Clinical Decision Support,” is available here.

Subsequently, Ahmed remained with the lab as a postdoctoral scholar at UCLA and an affiliated postdoctoral researcher at the University of Cambridge (COVID-19 task force). He received the 2021 Edward K. Rice Outstanding Doctoral Student Award from UCLA.

Ahmed then proceeded as a Postdoctoral Associate at the Broad Institute of MIT and Harvard, and the MIT Computer Science & Artificial Intelligence Laboratory (CSAIL).

He is now one of the inaugural Assistant Professors in the new computational precision health program at UC Berkeley and UCSF.

LinkedIn
GitHub
Google Scholar

Alexis Bellot

2017-2021 (Ph.D.)

Alexis joined the lab as a Ph.D. student in 2017, under the supervision of Mihaela van der Schaar and affiliated with the University of Cambridge and The Alan Turing Institute.

Alexis’ research consistently focused on causal inference, hypothesis testing, and its applications, most notably in healthcare. He awarded the G-research PhD competition prize in 2019.

In June 2021, Alexis was awarded his doctorate by the Department of Applied Mathematics and Theoretical Physics at the University of Cambridge following a successful defense of his thesis, entitled “Hypothesis testing and causal inference with heterogeneous medical data.”

Alexis then moved on to a postdoctoral research scientist at Columbia University, under the direction of Prof. Elias Bareinboim in the Computer Science Department. His research continued to focus on causal inference, hypothesis testing, and its applications.

Since then, Alexis has switched into the industry and is currently working with DeepMind in London.

LinkedIn
Google Scholar

Changhee Lee

2016-2021 (Ph.D.)

Changhee joined the lab as a Ph.D. student in 2016 (supervised by Mihaela van der Schaar) at the University of California, Los Angeles.

His research has focused on deep learning approaches for addressing challenges associated with modeling, predicting, and interpreting in time-to-event analysis and time-series analysis.

Changhee’s thesis, entitled “Machine Learning Frameworks for Data-Driven Personalized Clinical Decision Support and the Clinical Impact,” is available here.

Changhee is now an assistant professor in Chung-Ang University’s School of Software and Computer Engineering (Department of Artificial Intelligence).

LinkedIn
Google Scholar

James Jordon

2017-2021 (Ph.D.)

James joined the lab as a Ph.D. student in 2017 under Mihaela van der Schaar’s supervision at the University of Oxford.

Much of his research with the lab focused on the use of generative adversarial networks in solving supervised, unsupervised and private learning problems including estimation of individualised treatment effects, feature selection, private synthetic data generation, data imputation, and transfer learning.

James graduated on the basis of an integrated thesis comprised of multiple papers: GANITESCIGANGAINKnockoffGANPATEGAN, and DPBag.

James is now at The Alan Turing Institute, where he is pursuing a postdoc on synthetic data.

LinkedIn
GitHub
Google Scholar
Email

Trent Kyono

2018-2021 (Ph.D.)

Motivated by the desire to build cutting-edge machine learning models that can transform healthcare, Trent first joined the lab at the University of California, Los Angeles, under the supervision of Mihaela van der Schaar. He pursued a research agenda at the confluence of machine learning, computer vision, and causality.

Trent is a senior machine learning researcher within the Ads Ranking Team at Meta (Facebook) where he works on machine learning methods for ad personalization.

Trent’s dissertation, entitled “Towards Causally-Aware Machine Learning” focuses on leveraging cause and effect relationships for improving several aspects of machine learning, such as regularization, missing data, synthetic data, and domain adaptation.

Alumni (graduated pre-2020)

Post-docs
  • Dr. William Whoiles
    • Now Post-doc at the Department of Electrical and Electronics Engineering, University of British Columbia, Canada
  • Dr. Cem Tekin
    • Now Assistant Professor at the Department of Electrical and Electronics Engineering, Bilkent University, Turkey
  • Dr. Luca Canzian
    • Now Post-doc at the Computer Science Department, University of Birmingham, UK
Ph.D.
Affiliated Ph.D. Alumni
  • Dr. Cong Shen
    • Now Assistant Professor at University of Science and Technology China (USTC), China
  • Dr. Omar A. Nasr
    • Now Assistant Professor at Cairo University, Egypt
M.Sc.
Past visiting students
  • Minhae Kwon (2016) (Email)
  • Sabrina Muller (2015) (Email)
  • Suoheng Li (2014-2015) (Email)
  • Zhenlong Yuan (2014-2015) (Email)
  • Meier Yannick (2015) (Email)
  • Jonas Braun (2014) (Email)
  • SaiDhiraj Amuru (2014) (Email)
  • Mahnoosh Alizadeh (2013) (Email)
  • Cuiling Lan (2013) (Email)
  • Byung-Gook Kim (2012) (Email)
  • Luca Canzian (2012) (Email)
  • Saeede Parsaee Fard (2011) (Email)
  • Oussama Habachi (2011) (Email)
  • Ulrich Berthold (2008)(Email)
  • Elodie Heslouis (2005)
  • Aymeric Larcher (2004)