Damon Jude Wischik

Probabilistic machine learning

• PhD students, 2020—, have worked on adversarial attacks on neural networks, and on domain adaptation
• Part II and MPhil projects, 2023— on causal machine learning, and on uncertainty readouts from neural networks

How should we do science, when machines can learn much more accurate models of the world than humans can? I work on foundational questions at the intersection of machine learning and statistical theory: how to learn to distinguish cause and effect, and how to learn to estimate uncertainty. And I also work on applications, from road traffic to computer networks to climate science.

Climate modelling

• Artificial Intelligence for Environmental Risk (AI4ER) CDT, 2019–2025.

This CDT trained a cohort of students applying machine learning to climate science. I was on the management committee and the education committee, I was senior examiner for the MRes, and I taught the students data science and visualization. I supervised two PhD students, on machine learning for time series data as applied to global climate models. One of them is now working on wind-energy futures trading, the other is developing a startup for predicting extreme weather events.

Transport modelling and intervention

• Mobility Data Toolkit, funded by the Toyota Mobility Foundation via the Alan Turing Institute, £350k, 2020–2022.
• Urban Engines, a Bay Area startup, 2011–2016

At Urban Engines we build a platform for visualising and analysing big data about things that move: commuters, trains, buses, taxis, delivery fleets, etc. Customers included several major cities and transport infrastructure providers. We also ran an incentive scheme in Singapore for nudging commuter behaviour, reaching 20% of commuters. (This was the seed of my current interest in causal machine learning.) My later work on the Mobility Data Toolkit aimed to develop these ideas: to build a system that can handle user-histories as fluently as Excel handles tabular data. I also developed theory for modelling new services such as rideshare and dockless bikes: theory that combines models of user choice with models of network flow.

Computer network modelling

• at the Networks and Systems group in Computer Science at UCL, 2004–2011
• at Clockwork Systems Inc, a Bay Area startup, 2024–2025

I came to UCL with the goal of translating theoretical work on congestion control, begun by Prof. Frank Kelly in Cambridge, into a practical system. With Prof. Mark Handley and others in the EU-funded Trilogy project, we created MPTCP (Multipath TCP), which became an IETF standard and is used by the iPhone. I later joined Clockwork Systems as a consultant, bringing some of these ideas across to AI datacenter traffic management.

Clinical statistics

• Statistical consulting, 2006– for TauRx Therapeutics, a biotech startup based in Aberdeen, working on Alzheimer's Disease

This has involved interacting with medics, scientists, clinical research organisations, regulators, valuation consultants, and investment bankers, and has spanned Phase 2 and Phase 3 clinical trials. I have analysed data and advised on clinical trials, psychometrics, animal experiments, business development, risk and valuation. This work has given me a deep appreciation of statistics as a form of rhetoric, not just a tool for mathematical modelling.

Lecturing.

In my current post in the Computer Science department at Cambridge, I have taught • 1st year Algorithms • 1st year Scientific Computing • 2nd year Data Science • 3rd year Data Science and Visualization • a masters courses in Probabilistic Machine Learning. I have won the teaching innovation prize from the university (2023), and the teaching prize from my department (2025).

College.

I am a fellow of Christ's College, where I am currently Director of Studies for Computer Science. I won a prize for best supervisor (2024).

Students.

Six completed PhD students (Cambridge maths; UCL computer science; 4×Cambridge computer science). Assorted masters dissertations.

Department of Computer Science and Technology, University of Cambridge, 2017–: university lecturer

, working in the field of data science.

Alan Turing Institute, 2018–2022: fellow,

working on data science to model shared vehicle fleets and the future of transport, as part of the Urban Analytics research theme.

Urban Engines (a startup based in Los Altos, CA), 2011–2016: chief data scientist.

My work involved all levels of the stack: talking with customers, designing system capabilities, data architecture, devising visualisations and inference algorithms, and coding. The company had 22 employees, 10 of them in the data science group. Urban Engines was acquired by Google in 2016.

Electrical Engineering, Stanford: visiting professor in 2011, consulting professor in 2016.

In 2011 I worked with Prof. Balaji Prabhakar on societal networks—networks that combine real-world infrastructure and people. I worked on health incentives for Accenture employees, and transit incentives for Singaporean commuters. (This work led into Urban Engines, which Prof. Prabhakar cofounded.) In 2016, Prof. Prabhakar and I co-taught a course on Big Data for Things that Move, to graduate students in computing and engineering.

UCL, London, 2004–2011: Royal Society university research fellow,

based in the Networks and Systems group in the Computer Science department.

Trinity College, Cambridge, 1999-2004: Junior Research Fellow,

  an independent research position. I was based in the Statistical Laboratory in the University of Cambridge. I worked on probability theory for queueing networks, with application to Internet switches.

D.A. Iliescu and D.J. Wischik (2024). Style-Content Disentanglement Under Conditional Shift. ICLR. This paper addresses domain adaptation, the ML take on instrumental variable analysis.

Omer Nivron, Raghul Parthipan, Damon Wischik (2023). Taylorformer: Probabilistic Modelling for Random Processes including Time Series. ICML. This paper introduces the Taylorformer, a variant of the Transformer neural network architecture that's better suited to time series prediction tasks including climate modelling.

T.D.Grant and D.Wischik (2020). The path to AI: law's prophecies and the conceptual foundations of the machine learning age. Palgrave. The big novelty of machine learning—the elevation of prediction over explanation—was prefigured by Oliver Wendell Holmes Jr, a judge who reshaped American legal thinking at the end of the 19th century. The ensuing jurisprudential debates have much to offer machine learning.

T.D.Grant and D.Wischik (2020). Show us the data: privacy, explainability, and why the law can't have both. To appear in George Washington University Law Review. The GDPR requires that explanations be given of decisions given by machines—but for machine learning algorithms the only meaningful explanation involves sharing the training data.

Youngseo Kim, Ning Duan, Gioele Zardini, Samitha Samaranayake, Damon Wischik (2025). Strategic Pricing and Routing to Maximize Profit in Congested Roads Considering Interactions With Travelers. IEEE TCNS. This is the culmination of my 2018 work. It presents a unified view of the classic four-stage transport modelling approach, and treats it as a single ML-friendly optimization problem.

D.Wischik (2018). The price of choice: models, paradoxes, and inference for ‘mobility as a service’. Allerton. This paper unifies discrete choice modelling with network flow optimization, via information theory, in the context of rideshare modelling. It points the way to a comprehensive economic understanding of Mobility as a Service.

N.Gomes, D.Merugu et al. (2012). Steptacular: an incentive mechanism for promoting wellness. COMSNETS NetHealth. This is the only publication to come out of my work on incentives—but the system I built is running at www.travelsmartrewards.com, has 330,000 users, and has paid out $10M Singapore dollars over four years.

D.Wischik, C.Raiciu, and A.Greenhalgh (2011). Design, implementation and evaluation of congestion control for multipath TCP. NSDI, winner of best paper award. This work has been standardized as an Internet Experimental Standard, RFC 6356.

D.Shah and D.Wischik. Switched networks with maximum weight policies: fluid approximation and multiplicative state space collapse. Annals of Applied Probability (2012). Fluid models of congestion collapse in overloaded switched networks. Queueing Systems (2011).

C.M. Wischik, D.J. Wischik, J.M.D. Storey, C.R. Harrington (2010). Rationale for tau aggregation inhibitor therapy in Alzheimer's disease and other tauopathies. Chapter in Emerging drugs and targets for Alzheimer's disease, vol. 1, ed. A. Martinez, RSC Drug Discovery Series. I am a co-author on three patents relating to this work.

G.Raina, D.J.Wischik (2005). Buffer sizes for large multiplexers: TCP queueing theory and instability analysis. This work lead to a DARPA grant, and to a series of letters in ACM Computer Communication Review, co-authored with Nick McKeown and Don Towsley.

A.Ganesh, N.O'Connell, D.J.Wischik (2004). Big Queues, a book. Awarded the 2004 Best Publication Award by the Applied Probability Society of INFORMS.

Awards

Royal Society University Research Fellowship, 2004–2011.
Trinity College Junior Research Fellowship, 1999–2003
Best Publication Award from the Applied Probability Society of INFORMS in 2005, for Big Queues, a book arising from my PhD work.
Best Paper Award at NSDI 2011, for Design, implementation and evaluation of congestion control for multipath TCP. This paper later won the 2022 Test of Time award.

Trinity College, Cambridge, 1996-1999: PhD

  in the Statistical Laboratory, supervised by Prof. Frank Kelly. My thesis was titled Large Deviations and Internet Congestion.

[degree certificate]

Trinity College, Cambridge, 1992-1996: BA in Mathematics.

Specialising in applied probability, statistical inference, and optimization.

Awards

—  Mayhew Prize for top final-year result in Applied Mathematics.

[academical record]