Oleksandr Shchur

Applied Scientist at AWS AI.

profile_pic.webp

I’m an Applied Scientist at AWS AI in Berlin, where I work on AutoGluon. Currently my research focuses on time series forecasting and AutoML.

I did a PhD in machine learning at the Technical University of Munich, supervised by Stephan Günnemann. During my PhD I primarily worked on temporal point processes (TPPs) — probabilistic models for continuous-time event sequences, such as user activity on social media or earthquake sequences in seismology.

If you want to learn more about my research, have a look at my blog or my PhD thesis.

news

Sep 04, 2024 I have presented our latest work on time series forecasting at the AutoML Summer School in Hannover & AutoML Conference in Paris (slides).
Apr 17, 2024 We have released AutoGluon v1.1, now including pretrained models for time series forecasting!
Mar 31, 2024 We have released Chronos, a family of pretrained models for time series forecasting (code, 🤗 model weights)

latest posts

selected publications

  1. arXiv
    Chronos: Learning the language of time series
    Abdul Fatir Ansari, Lorenzo Stella, Caner Turkmen, and 8 more authors
    2024
  2. AutoML
    AutoGluon–TimeSeries: AutoML for probabilistic time series forecasting
    Oleksandr Shchur, Ali Caner Turkmen, Nick Erickson, and 4 more authors
    In International Conference on Automated Machine Learning, 2023
  3. NeurIPS
    Fast and Flexible Temporal Point Processes with Triangular Maps
    Oleksandr Shchur, Nicholas Gao, Marin Biloš, and 1 more author
    In Neural Information Processing Systems, NeurIPS, 2020