siu lun chau




Welcome

Hello! My name is Siu Lun Chau (周兆麟), currently a postdoctoral researcher at the Rational Intelligence Lab within CISPA Helmholtz Center for Information Security in Germany. I work under the guidance of Dr. Krikamol Muandet, focusing on developing machine learning models that acknowledge what they don't know, and effectively communicating what they know. To achieve this goal, we need better methods for modelling **uncertainty**, **explanability**, and **preferences**.

Before joining CISPA, I obtanied my DPhil in Statistical Machine Learning from the University of Oxford, where I specialised in kernel methods and Gaussian processes under the supervision of Prof. Dino Sejdinovic. I also interned at Amazon as an Applied Scientist, where I tackled coherent forecasting problems for the EU logistics network. I also interned at the Max Planck Institute for Intelligent Systems, where I worked on improving econometric models with modern machine learning approaches.

I hold both a master's and undergraduate degree in Mathematics and Statistics with First Class Honours from the University of Oxford. During my master's, I worked with Prof. Mihaela van der Schaar on modelilng diseases trajectories using Bayesian nonparametric methods.

You can read more about my research interests here. Please do not hesitate to reach out if you would like to collaborate, I am always excited to hear from you :)


Recent Updates 🔔

May-2024

Our paper Domain Generalisation via Imprecise Learning has been accepted as a spotlight paper for publication at the International Conference on Machine Learning (ICML) 2024! 🎉

Feb-2024

I presented “Stochastic Shapley values for Gaussian process models with application to Explainable Bayesian Optimisation” at the Institute for Informatics, LMU.

Feb-2024

I was invited to participate in the Dagstuhl Seminar on ‘AI for Social Good’ this year to learn about and tackle challenges faced by NGOs when implementing AI solutions.

Jan-2024

Our paper ‘Looping in the Human: Collaborative and Explainable Bayesian Optimization’ has been accepted for in AISTATS for poster presentation!

Dec-2023

Our paper ‘Causal Strategic Learning with Competitive Selection’ has been accepted for in AAAI as an oral paper!

Dec-2023

I’m excited to present a poster spotlight on ‘Explaining Gaussian Process Models with Stochastic Shapley Values’ at the Australian Data Science Network conference.

Nov-2023

I am at the Australian Institute for Machine Learning 🇦🇺 as a visiting researcher from November onwards!

Sep-2023

Our paper ‘Explaining the Uncertain: Stochastic Shapley values for Gaussian process models’ has been accepted for in Neural Information Processing Systems (NeurIPS) as a spotlight paper!

Sep-2023

Our paper “Gated Domain Units for Multi-source Domain Generalization” has been accepted for publication in Transactions on Machine Learning Research (TMLR).

Sep-2023

I have officially started my postdoc at CISPA! 👨🏻‍

Jul-2023

I have passed my Ph.D. viva!


Upcoming/Recent Talks 🗣️

Aug-2024
Introduction to the role of Uncertainty in Machine Learning
- Kernels and Information Processing Systems group, University of Adelaide
Jul-2024
Introduction to the role of Uncertainty in Machine Learning
- College of Computing and Data Science, Nanyang Technological University
Mar-2024
Stochastic Shapley Values for Gaussian Processes and application to Explainable Bayesian Optimisation
- Institute for Informatics, LMU
Dec-2023
Stochastic Shapley Values for Gaussian Processes
- Australian Data Science Network
Nov-2023
Collaborative and Explainable Bayesian Optimisation
- Data 61 Melbourne
Nov-2023
Stochastic Shapley Values for Gaussian Processes
- School of Computing, Australian National University
Nov-2023
Collaborative and Explainable Bayesian Optimisation
- School of Computing and Information Systems, The University of Melbourne
Nov-2023
Stochastic Shapley Values for Gaussian Processes
- Australian Institute for Machine Learning (AIML)
Sep-2023
Stochastic Shapley Values for Gaussian Processes
- Oxford Man Institute, University of Oxford
Sep-2023
Stochastic Shapley Values for Gaussian Processes
- ETH AI Center
Sep-2023
Stochastic Shapley Values for Gaussian Processes
- Department of Management, Technology, and Economics (D-MTEC) at ETH Zürich
Feb-2023
Introduction to Explainable ML
- Oxford Strategy Group Digital
Feb-2023
Explaining kernel methods and preference models with RKHS-SHAP
- CISPA Helmholtz Center for Information Security
Sep-2022
Explainability for kernel methods
- ELISE Theory Workshop on ML fundamentals at Eurecom
Sep-2022
Spectral ranking with Covariates
- ECML-PKDD
Jun-2022
Deconditional Gaussian processes
- S-DCE Alan Turing Institute seminar
Apr-2022
Explaining kernel methods with RKHS-SHAP
- UCL Gatsby Unit
Feb-2022
Shapley values for model explanations
- Imperial & Oxford STATML seminar
Jun-2021
Uncertainty quantification for causal data fusion
- Warwick ML group