About Me

I am a PhD student at the Australian National University, under the supervision of Richard Nock, Ke Sun, and Lexing Xie. I am interested in a wide range of research topics. Previously I have worked on topics including formal methods / theorem provers, visualisation in academic influence, knowledge graphs, and universal approximation theorems. I am also interested in point process models. My primary focus is on utilising boosting algorithms, information geometric tools, and the theory of loss functions with a focus on fairness and privacy in machine learning.

Publications


  1. Fair Densities via Boosting the Sufficient Statistics of Exponential Families
    • Alexander Soen
    • Hisham Husain
    • Richard Nock
    International Conference on Machine Learning, 2023
  2. Fair Wrapping for Black-box Predictions
    • Alexander Soen
    • Ibrahim Alabdulmohsin
    • Sanmi Koyejo
    • Yishay Mansour
    • Nyalleng Moorosi
    • Richard Nock
    • Ke Sun
    • Lexing Xie
    Advances in Neural Information Processing Systems, 2022
  3. Interval-censored Hawkes processes
    • Marian-Andrei Rizoiu
    • Alexander Soen
    • Shidi Li
    • Pio Calderon
    • Leanne Dong
    • Aditya Krishna Menon
    • Lexing Xie
    Journal of Machine Learning Research, 2022
  4. On the Variance of the Fisher Information for Deep Learning
    • Alexander Soen
    • Ke Sun
    Advances in Neural Information Processing Systems, 2021
  5. UNIPoint: Universally Approximating Point Processes Intensities
    • Alexander Soen
    • Alexander Mathews
    • Daniel Grixti-Cheng
    • Lexing Xie
    Proceedings of the AAAI Conference on Artificial Intelligence, 2021
  6. Influence flowers of academic entities
    • Minjeong Shin
    • Alexander Soen
    • Benjamin T Readshaw
    • Stephen M Blackburn
    • Mitchell Whitelaw
    • Lexing Xie
    IEEE conference on visual analytics science and technology (VAST), 2019

Preprints


  1. Linking Across Data Granularity: Fitting Multivariate Hawkes Processes to Partially Interval-Censored Data
    • Pio Calderon
    • Alexander Soen
    • Marian-Andrei Rizoiu
    arXiv preprint arXiv:2111.02062, 2021