Paul E. Chang

Hi! My name is Paul and I am an almost post-doc working in Machine and Human Intelligence group at the University of Helsinki, Finland. Previouly, I was a PhD student in Arno Solin's research group at Aalto University, Finland. I am interested in the intersection of probabilistic modelling and foundation models (GenAI). Please get in touch to talk about research or anything.

Email  /  Google Scholar  /  LinkedIn

News

  • [May 2024] Aidan Scannel*, Riccardo Mereu*, Paul E. Chang , Ella Tamir and Arno Solin. Function-space Parameterization of Neural Networks for Sequential Learning (ICLR), 2024. Link  
  • [May 2023] Paul E. Chang *, Prakhar Verma*, ST John, Arno Solin, and Mohammad Emtiyaz Khan. Memory-based dual Gaussian processes for sequential learning accepted in International Conference on Machine Learning (ICML), 2023 (Oral Presentation). Link  
  • [January 2023] One month research visit with Emtiyaz Khan at RIKEN AIP, Japan.
  • [November 2022] Prakhar Verma, Paul E. Chang, Arno Solin, Mohammad Emtiyaz Khan. Sequential Learning in GPs with Memory and Bayesian Leverage Score accepted in Asian Conference in Machine Learning (ACML) workshop "Continual Lifelong Learning" 2022 (Contributed talk). Link  
  • [October 2022] Paul E. Chang, Prakhar Verma, ST John, Victor Picheny, Henry Moss, Arno Solin. Fantasizing with Dual GPs in Bayesian Optimization and Active Learning accepted in NeurIPS workshop "Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems" 2022. Link  
  • [October 2021] Vincent Adam*, Paul Chang*, Emtiyaz Khan, Arno Solin. Dual Parameterization of Sparse Variational Gaussian Processes accepted in NeurIPS 2021. Link