July 27, 2022
We are thrilled to share that LIDS faculty member Guy Bresler was granted tenure by the Department of Electrical Engineering and Computer Science, effective July 1, 2022. Guy is also a faculty member in the Institute for Data, Systems, and Society (IDSS).
Guy joined MIT and LIDS as faculty in 2015 and has made tremendous contributions to the community in this time. “Guy is an exceptional researcher, dedicated mentor, and wonderful colleague,” said LIDS director Sertac Karaman. “I feel lucky to have known him since the very start of his career and know that he will continue to bring his keen intellect, kindness, and enthusiasm to all that he does.”
In his announcement, IDSS director Munzer Dahleh shared a brief synopsis of Guy’s career and achievements so far:
Guy received his PhD from the University of California, Berkeley in 2012. After graduation, he was a postdoctoral fellow at MIT until 2015, when he joined MIT as an Assistant Professor in EECS and core faculty member of IDSS. He was promoted to Associate Professor without tenure in July 2019. Guy’s research area is at the intersection of the fields of high-dimensional statistical inference and computation. His work considers the two key factors for an inference or learning task to be possible: (1) informational/statistical complexity (does the data contain enough information for the task to be in principle feasible) and (2) computational complexity (does the problem have a structure that can be exploited in order to obtain computationally feasible algorithms). Guy has made several central contributions to this field. In the context of graphical models, he demonstrated the surprising result that learning an Ising model (an important probabilistic model where each node of the graph is a random variable taking two discrete values) can be done efficiently for models with bounded degree. He recently extended these results to Ising models with latent (unobservable) variables. In the last several years, Guy focused his research in the area of Statistical-to-Computational tradeoffs, an emerging area addressing questions related to computational hardness for certain high dimensional statistical problems. In this context, Guy developed a comprehensive ‘average case complexity’ theory that maps out a rich web of relations between important statistical problems such as sparse PCA, community detection, bi-clustering, and others, ultimately showing that these problems are at least as hard as the problem of discovering a planted clique in a random graph.
Guy is the co-chair of the Machine Learning and Inference student admission group in EECS, and a member of the curriculum committee in AI+D; he has organized external seminars in both LIDS and SDSC. Additionally, he has taught and developed multiple classes in EECS, including Probability Theory, Machine Learning, Algorithms For Inference, and Discrete Stochastic Processes, and has contributed to the curriculum of all of these classes. Guy was awarded the COLT (Conference on Learning Theory) Best Student Award in 2018 and 2020, and the NSF CAREER award in 2020.
Please join us in congratulating Guy on this much-deserved accomplishment — we look forward to his many achievements to come!