About Me

I’m a PhD student in Machine Learning under the Cambridge-Tübingen PhD Fellowship, studying at Machine Learning Group, Computational and Biological Learning Lab, University of Cambridge and Department of Empirical Inference, Max Planck Institute for Intelligent Systems. My supervisors are José Miguel Hernández-Lobato, Bernhard Schölkopf, and Hong Ge.

I’m keen on basic research in machine learning and its scientific applications. My research interest lies at the intersection of deep learning and probabilistic methods. I’m exicted about developing efficient machine learning methods for robust prediction and realistic data generation.

Interests
  • Deep Probabilistic Modeling
  • Meta/Multi-Task Learning
  • Generative Modeling
  • Sampling
  • Optimization
  • AI for Science
Education

  • PhD in Machine Learning

    University of Cambridge & Max Planck Institute for Intelligent Systems

  • MPhil in Machine Learning and Machine Intelligence, Distinction, 2021

    University of Cambridge

  • BSc (Hons) in Mathematics, First Class Honors, 2020

    University of Manchester

Experience

 
 
 
 
 
Doctoral Researcher - Machine Learning
Department of Empirical Inference, Max Planck Institute for Intelligent Systems
Oct 2021 – Present Tübingen, Baden-Württemberg, Germany
Deep Learning, Generative Modeling, Sampling, AI for Science
 
 
 
 
 
Research Intern - AI for Science
Microsoft Research AI4Science
Mar 2024 – Jun 2024 Haidian, Beijing, China
Molecular Dynamics and Machine Learning Force Field
 
 
 
 
 
Research Intern - Optimization
CEMSE, King Abdullah University of Science and Technology (KAUST)
Sep 2020 – Oct 2020 Remote
Federated Learning and Distributed Optimization
 
 
 
 
 
Research Engineer Intern - Deep Learning
Imagination Technologies
Jun 2019 – Aug 2019 Kings Langley, England, United Kingdom
Deep Learning on Edge Devices

Selected Publications

See my Google Scholar profile or publication page for a complete list of papers.
Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks
NeurIPS 2024
Wenlin Chen, Hong Ge
PDF Cite Code OpenReview arXiv
Leveraging Task Structures for Improved Identifiability in Neural Network Representations
TMLR 2024
Wenlin Chen*, Julien Horwood*, Juyeon Heo, José Miguel Hernández-Lobato
PDF Cite Code OpenReview arXiv
Modelling Variability in Human Annotator Simulation
ACL 2024
Wen Wu*, Wenlin Chen*, Chao Zhang, Philip C. Woodland
PDF Cite Code ACL Anthology arXiv
Diffusive Gibbs Sampling
ICML 2024
Wenlin Chen*, Mingtian Zhang*, Brooks Paige, José Miguel Hernández-Lobato, David Barber
PDF Cite Code PMLR OpenReview arXiv
Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction
ICLR 2023
Wenlin Chen, Austin Tripp, José Miguel Hernández-Lobato
PDF Cite Code Slides OpenReview arXiv
Optimal Client Sampling for Federated Learning
TMLR 2022
Wenlin Chen, Samuel Horváth, Peter Richtárik
PDF Cite Code Video OpenReview arXiv
To Ensemble or Not Ensemble: When Does End-to-End Training Fail?
ECML 2020
Andrew Webb, Charles Reynolds, Wenlin Chen, Henry Reeve, Dan Iliescu, Mikel Luján, Gavin Brown
PDF Cite Code Video Springer Link arXiv

Awards

Stars of Tomorrow Award
Microsoft Research Asia Jul 2024
Cambridge University Engineering Department PhD Studentship
Department of Engineering, University of Cambridge May 2021
Cambridge Trust Scholarship
Cambridge Commonwealth, European and International Trust Apr 2021
Cambridge-Tübingen PhD Fellowship in Machine Learning
Department of Empirical Inference, Max Planck Institute for Intelligent Systems Feb 2021
The Royal Statistical Society Prize
The Royal Statistical Society Jul 2020
International Mathematics Scholarship
Department of Mathematics, University of Manchester Aug 2019

Contact