Andrej Risteski is an Assistant Professor in the Machine Learning Department at Carnegie Mellon University. Prior to joining Carnegie Mellon, he was the inaugural Norbert Wiener Research Fellow jointly in the Applied Math department at MIT, and the Institute for Data Science and Statistics (IDSS). He received his PhD in Computer Science in Princeton University under the advisement of Sanjeev Arora, where he also received his Bachelor’s degree in Computer Science.
His broad area of research concerns mathematical and scientific foundations of machine learning and artificial intelligence, with aparticular focus on deep learning and neural networks. He publishes in flagship conferences for machine learning, like NeurIPS, ICMLand ICLR, as well as flagship theoretical computer science conferences like STOC and COLT. He also regularly serves in program and reviewing committees for such conferences.
Topics he has published on include (probabilistic) generative models, self-supervised and representation learning, designing and analyzing algorithmic tools for learning and inference using stochastic differential equations, robustness and out-of-distribution generalization, and applications of neural approaches to natural language processing and scientific domains.