In my scientific work, I have largely focused on the role of optimization in the success of deep learning. My main contribution is largely resolving the mystery why learning rate, a fundamental hyperparameter, impacts generalization in deep learning. In the process we have discovered that all deep learning trainings go through chaotic phase in the beginning of training. This in particular has been part of Understanding Deep Learning book (Prince, MIT press). For more details see our ICLR 2020 paper (spotlight). This is closely related to the Edge of Stability phenomenon.
I do my best to contribute to the broad machine learning community. Currently, I serve as an Action Editor for TMLR and an area chair for ICLR 2023 (before that NeurIPS 2020-23, ICML 2020-22, ICLR 2020-22).