Jean Honorio

Assistant Professor in the Computer Science Department at Purdue.
Assistant Professor in the Statistics Department (by courtesy) at Purdue.
Lawson Building 2142-J, West Lafayette, IN 47907, phone: 765-496-6757
e-mail: jhonorio at purdue.edu

Modern machine learning (ML) problems are combinatorial and non-convex, for which theoretical guarantees are quite limited. Furthermore, while quantitative guarantees (e.g., small test error) have been studied, qualitative guarantees (e.g., correctness of clustering) are mostly lacking. My long-term research goal is to uncover the general foundations of ML and optimization that drives the empirical success across many specific combinatorial and non-convex ML problems. I aim to develop a set of optimization-theoretic frameworks and tools to bridge the aforementioned gaps, to further our understanding of continuous (possibly non-convex) relaxations of combinatorial problems, as well as our knowledge of non-convexity.

My aim is to generate correct, computationally efficient and statistically efficient algorithms for high dimensional ML problems. My research group has produced breakthroughs not only on classical worst-case NP-hard problems, such as learning and inference in structured prediction, community detection and learning Bayesian networks, but also on areas of recent interest such as fairness, meta learning and federated learning. [vita]

Prior to joining Purdue, I was a postdoctoral associate at MIT CSAIL, working with Tommi Jaakkola. My Erdős number is 3: Jean Honorio → Tommi Jaakkola → Noga Alon → Paul Erdős.

A Note for Prospective Students

Here is a note for students who are considering working with me.

Students that work with me should have knowledge of: I require students to be: To have a more detailed idea about my work, please see: To have a more detailed idea about the tools I use for proving theorems, please see: If the above still makes sense, and you have looked at my papers and seminar, please contact me.