![Featured image for “[PhD] Two New ORAI PhD Courses Offered This Spring”](https://www.cs.usc.edu/wp-content/uploads/2025/06/USC-Featured-Photo.png)
The following announcement is from [ORAI Program]. Please contact them directly if you have any questions.
Dear CS PhD students,
Happy end of semester!
I want to bring to your attention two new PhD CS classes that were developed as a part of the ORAI program that may be of interest to many of your PhD students, as they cover the latest research developments at the intersection of ML and decision-making/operations research.
Please consider recommending these to your students.
We hope to build up this new program, and we can benefit from a healthy enrollment. Your help is appreciated!
- ISE/CSCI 617 (Profs. Andres Gomes/Bistra Dilkina): Machine Learning for/with Mixed-Integer Optimization (M/W 12-1:50)
- The course will cover recent results on combining the strengths of Machine Learning (ML)/ Artificial Intelligence (AI) and Mixed-Integer Optimization (MIO) technologies. It will discuss how MIO can be used to enhance AI methods in settings with scarce and unreliable data, in high-stakes situations where interpretability and fairness play fundamental roles, and when tackling engineering problems requiring human-AI collaborations. The course will also discuss how AI can be used to improve solving MIO and other combinatorial problems, using it to learn ML-based alternatives to key heuristic components of solvers such as branching, understand the key structural properties of a given instance, effective configurations of MIO solvers, and predict the performance of a given algorithm, thus improving decision-making throughout the solution process.
- CSCI/ISE/DCO 619 (Prof. Vishal Gupta): End-to-End Learning and Optimization (M/W 2-3:50)
- Models and algorithms for end-to-end learning from operations research and machine learning perspectives. Decision-aware learning is an emerging paradigm in AI that seeks to blend the strengths of both approaches. The best way to do so is still an active area of research. Students will learn about using “optimization layers” in deep learning architectures, designing custom convex surrogates for the decision loss of certain classes of optimization problems, debiasing techniques for model-agnostic policy learning, and even “light touch” adaptations of traditional predict-then-optimize pipelines. These methods have shown great empirical success in large-scale supply-chain problems, robotic control, energy-systems planning, and more. In this course, we will develop these approaches rigorously and learn about their applications. We pay special attention to algorithmic / computational aspects and their statistical properties/performance guarantees. Much of the course focuses on modeling considerations and how to identify applications that are amenable to an “end-to-end learning” perspective. We aim to empower students to apply state-of-the-art methods and conduct novel research in this area.