Siyuan Guo

PhD student in Computer Science

University of Cambridge

Max Planck Institute for Intelligent Systems

Biography

I am a Cambridge-Tübingen Fellow at the Max Planck Institute for Intelligent Systems and the University of Cambridge, supervised by Bernhard Schölkopf and Ferenc Huszár. Previously I worked on fairness with Ricardo Silva at UCL and variable selection in high-dimensional statistics with Richard Samworth.

My research interests are on scientific induction (a.k.a causality) and non-i.i.d. data. I am interested in incorporating causality in machine learning models and understanding causality in non-i.i.d. data: from Causal de Finetti (NeurIPS 2022) to Do Finetti, from out-of-distribution to out-of-variable (ICLR 2023).

List of recent news:

2024-07-22 Off to FAIR Meta, NYC.
2024-07-19 Invited to lecture at Cambridge Ellis Summer School.
2024-07-05 Received the MPI-IS Outstanding Female Doctoral Student Prize!!

I take great pleasure in (co-)mentoring a few talented and highly motivated students. It has been a great privilege for me to constantly learn and get inspired by them. Here is a list of students I am working with in time-wise order:

Anna Kerekes, PhD student at ETH Zurich, Feb 2024 - now
Szilvia Ujváry, PhD student at Cambridge, Feb 2024 - now
Davin Xianjun Choo, PhD student at NUS, Jun - Aug 2023

Application For motivated students interested in working on causality and / or machine learning, feel free to reach out via sguo26v@gmail.com. Internship is possible to be hosted at beautiful MPI.

Interests

Causality
Scientific Induction
Machine Learning
Non-I.I.D. Data

Education

PhD in Computer Science, 2021
University of Cambridge & Max Planck Institute for Intelligent Systems
Msc in Machine Learning, 2020
University College London
Bachelor and Master in Mathematics, 2015
University of Cambridge

Recent Publications

Visit my Google Scholar profile or search over my publication page.

Siyuan Guo, Viktor Tóth, Bernhard Schölkopf, Ferenc Huszár (2023). Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Data. In Advances in Neural Information Processing Systems (NeurIPS), 2023.

PDF Cite Code

Siyuan Guo, Jonas Wildberger, Bernhard Schölkopf (2023). Out-of-Variable Generalization for Discriminative Models. arxiv preprint 2304.07896.

PDF Cite

Andrei Palayes, Siyuan Guo, Bernhard Schölkopf, Neil Lawrence (2023). Dataflow graphs as complete causal graphs. In IEEE/ACM 2nd International Conference on AI Engineering–Software Engineering for AI (CAIN), 2023.

PDF Cite Code

Jonas Wildberger, Siyuan Guo, Bernhard Schölkopf (2023). On the Interventional Kullback-Leibler Divergence. In 2nd Conference on Causal Learning and Reasoning (CLeaR), 2023.

PDF Cite

Limor Gultchin, Siyuan Guo, Alan Malek, Silvia Chiappa, Ricardo Silva (2022). Pragmatic Fairness: Optimizing Policies with Outcome Disparity Control. In NeurIPS 2022 Workshop on Algorithmic Fairness through the Lens of Causality and Privacy.

PDF Cite Code

See all publications