Sorawit (James) Saengkyongam

Doctoral Student at ETH Zürich; Research Intern at Apple Health AI.

prof_pic.jpg

I’m a last year PhD student at ETH Zürich, Seminar for Statistics supervised by Jonas Peters. I’m currently interning at Apple in the Health AI team working with Christina Heinze-Deml.

During my PhD studies, I spent my first two years at Copenhagen Causality Lab and did a research visit with Pradeep Ravikumar at Carnegie Mellon University’s Machine Learning Department and with Susan Murphy at the Statistical Reinforcement Learning Lab, Harvard University.

I completed my master’s degree in Machine Learning at University College London, during which I worked with Ricardo Silva. Prior to the master’s studies, I worked as a data scientist at Agoda for four years. I received my bachelor’s degree in Statistics from Chulalongkorn University.

My research interest lies in the intersection between Causality, Invariance and Robustness in Machine Learning.

Publications

Journal Articles

2024

  1. JMLR
    Effect-Invariant Mechanisms for Policy Generalization
    Sorawit Saengkyongam, Niklas Pfister, Predrag Klasnja, Susan Murphy, and Jonas Peters
    Journal of Machine Learning Research, 2024
  2. JASA
    Model-based Causal Feature Selection for General Response Types
    Lucas Kook, Sorawit Saengkyongam, Anton Rask Lundborg, Torsten Hothorn, and Jonas Peters
    Journal of the American Statistical Association, 2024

2023

  1. TPAMI
    Invariant Policy Learning: A Causal Perspective
    Sorawit Saengkyongam, Nikolaj Thams, Jonas Peters, and Niklas Pfister
    IEEE transactions on pattern analysis and machine intelligence, 2023
  2. JRSS-B
    Statistical Testing under Distributional Shifts
    Nikolaj Thams, Sorawit Saengkyongam, Niklas Pfister, and Jonas Peters
    Journal of the Royal Statistical Society Series B: Statistical Methodology, 2023

2021

  1. JMLR
    Counterfactual Mean Embeddings
    Krikamol Muandet, Motonobu Kanagawa, Sorawit Saengkyongam, and Sanparith Marukatat
    Journal of Machine Learning Research, 2021

2019

  1. CompStat
    Efficient Computation of the Stochastic Behavior of Partial Sum Processes
    Sorawit Saengkyongam, Anthony Hayter, Seksan Kiatsupaibul, and Wei Liu
    Computational Statistics, 2019

Conference Articles

2024

  1. ICLR
    Identifying Representations for Intervention Extrapolation
    Sorawit Saengkyongam, Elan Rosenfeld, Pradeep Ravikumar, Niklas Pfister, and Jonas Peters
    International Conference on Learning Representations, 2024

2022

  1. ICML
    Exploiting Independent Instruments: Identification and Distribution Generalization
    Sorawit Saengkyongam, Leonard Henckel, Niklas Pfister, and Jonas Peters
    In International Conference on Machine Learning , 2022

2020

  1. UAI
    Learning Joint Nonlinear Effects from Single-variable Interventions in the Presence of Hidden Confounders
    Sorawit Saengkyongam, and Ricardo Silva
    In Conference on Uncertainty in Artificial Intelligence , 2020