Ambrish’s research interests lie in Machine Learning and its applications. Most recently, his focus has been on Adversarial Machine Learning and Federated Learning especially in the context of Deep Learning. Previously, he has worked in Automated Machine Learning and Bayesian Deep Learning. He is passionate about ensuring security and privacy guarantees in ML applications and his work includes research projects on the robustness of ML against adversarial attacks e.g. poisoning in Deep Generative Models and Federated learning systems, and mitigation of privacy issues e.g. via differentially private mechanisms.
He holds a Master of Philosophy in Machine Learning and Machine Intelligence from the University of Cambridge, UK, and a Master of Technology in Mathematics and Computing from the Indian Institute of Technology, Delhi (IIT Delhi). He joined IBM in 2016 and has been part leading and contributing towards efforts in AI and ML at the Dublin Research Laboratory.
Ambrish has extensively published his work at top AI conferences, filed multiple US and international patents, and is an active contributor to open source software projects. He is a program committee member for top-tier conferences in ML including ICLR, ICML, NeurIPS, IJCAI and AAAI, and IEEE Transactions on Pattern Analysis and Machine Intelligence. He has been recognised with IBM Research Division Award and several Outstanding Technical Accomplishment Awards for his contributions to the vast array of cutting-edge research at IBM.