Overview
This postdoctoral position at ESSEC Business School offers a unique opportunity to engage in cutting-edge research at the intersection of machine learning and optimization. The project, titled Learn2Opt, aims to develop sustainable optimization techniques enhanced by machine learning, addressing significant challenges in computational efficiency and environmental impact.
Background & Relevance
The integration of machine learning into optimization processes is increasingly vital in various fields, including logistics, transportation, and resource management. Traditional optimization methods often struggle with high computational costs and energy consumption, particularly when applied to large-scale decision-making problems. This research initiative seeks to innovate within this space, aiming to create more efficient algorithms that not only improve solution quality but also consider the sustainability of training machine learning models.
Key Details
- Host Institution: ESSEC Business School
- Location: Paris Area, France
- Starting Date: September–November 2025 (flexible)
- Duration: 18 months (with a potential extension of up to 1 additional year)
- Project Focus: Development of ML-augmented optimization frameworks using decomposition methods.
Eligibility & Participation
This position is targeted at highly motivated individuals with a PhD in Operations Research, Machine Learning, Applied Mathematics, Computer Science, or related fields. Candidates should have a solid background in mathematical optimization and machine learning, along with excellent coding skills, preferably in Python or Julia. Familiarity with decomposition methods, active learning, or reinforcement learning will be advantageous.
Submission or Application Guidelines
Interested candidates should send their applications to emiliano.traversi@essec.edu with the subject line “Postdoc Application – Learn2Opt.” Applications should include:
– A detailed CV
– A one-page motivation letter
– Names and contact information for two references
– (Optional) Up to two representative publications
The position will remain open until filled.
More Information
The project will utilize the Stochastic Dial-a-Ride Problem (SDARP) as a case study, reflecting real-world complexities in urban transportation systems. By focusing on integrating Active Learning and Reinforcement Learning, this research aims to set new standards for efficiency and sustainability in optimization methodologies.
Conclusion
This postdoctoral position represents a significant opportunity for researchers interested in the innovative application of machine learning to optimization challenges. Interested individuals are encouraged to apply and contribute to this impactful research initiative at ESSEC Business School.
Category: PhD & Postdoc Positions
Tags: machine learning, optimization, active learning, reinforcement learning, operations research, decomposition methods, ESSEC Business School, urban transportation, data-efficient training, scientific publications
