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
Through a unifying framework, with the power of continuous relaxations (beyond convexity) and primal-dual certificates, my research group produces novel algorithms for learning and inference in combinatorial problems. Our aim is to generate correct, computationally efficient and statistically efficient algorithms for high dimensional machine learning problems. We have 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:
- linear algebra (e.g., eigenvalues, Hessian, gradients.)
- discrete math (e.g., graphs, proof by contradiction, proof by induction.)
- theory of algorithms (e.g., computational complexity.)
- experience in proving theorems (by already submitted or accepted papers) is highly encouraged, although not required.
- good programming experience (e.g., C++ or Matlab.)
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.
- avid readers of the literature (e.g., NeurIPS, ICML, AISTATS, UAI, JMLR.)
- self-motivated, committed, hard working individuals.