Adel Elmahdy

Adel received a Ph.D. candidate at the University of Minnesota. His research interests span a broad range of topics focusing largely on information theory and coding, and its applications in machine learning such as active learning for ranking from noisy pairwise comparisons; coded data shuffling for distributed machine learning; and matrix completion with graph side information for recommender systems. Recently, He embarked on new research directions in privacy-preserving natural language processing at Microsoft Research (MSR), and graph neural networks at Amplitude Analytics. In the past, He conducted research in the field of wireless communication theory. His research work has been published in top-tier machine learning conferences (NeurIPS, ICML, NAACL), as well as information theory conferences and journals (ISIT, ITW, IEEE Transactions in Information Theory).