Koustuv Sinha (McGill University)


Koustuv Sinha is a Ph.D. Candidate at McGill University / Mila, supervised by Dr. Joelle Pineau and Dr. William L. Hamilton, and currently a research intern at Facebook AI Research, Montreal. His primary research interest lies in advancing logical generalization capabilities of neural models in discrete domains, such as language and graphs. He is also involved in organizing annual Machine Learning Reproducibility Challenge and is serving as Reproducibility Co-Chair at NeurIPS 2019 and 2020.


Reproducibility in Machine Learning: From Theory to Practice

[slides, video]

Abstract: A recurrent challenge in machine learning research is to ensure that the presented and published results are reliable, robust, and reproducible. Reproducibility, which is obtaining similar results as presented in a paper or talk, using the same code and data (when available), is a necessary step to verify the reliability of research findings. Reproducibility is also an important step to promote open and accessible research, thereby allowing the scientific community to quickly integrate new findings and convert ideas to practice. Reproducibility also promotes the use of robust experimental workflows, which potentially reduce unintentional errors. In this talk, I will first present some statistics on the need for reproducibility in machine learning research, and then cover the recent approaches taken by the community to promote reproducible science. Finally, I will talk in-depth about the experimental workflows that you can integrate with your research, to ensure and promote reproducible science.