IVADO is supporting this research program with $1.2M as part of our Strategic Research Funding Program launched in 2021. We invite you to visit the program’s main page to view its objectives and better understand the process that supported this project.
Program description
Nearly all decision problems involve some form of uncertainty. This is especially true in supply chains where, e.g., demand, cost, capacity, and travel time’s high variability considerably complicate the planning of procurement, production, distribution, and service activities. Due to constantly evolving environments and the high frequency of data acquisition, classical decision-making that is based on training models, validating them, to finally optimize decisions does not suffice anymore. This research program aims at developing new methods for making the most effective and adaptive use of data in decision-making. It is founded on modern optimization and machine learning perspectives that encompasses developments in deep reinforcement/end-to-end learning, risk averse decision theory, and contextual/distributionally robust optimization. Its mission is three-fold: (i) develop the next generation of methods to deal with uncertainty in data-driven risk-aware optimization models by integrating machine learning; (ii) identify scientifically challenging and high-impact opportunities for improving robustness in supply chains; and finally (iii) stimulate the integration of stochastic optimization models among our partners while defining use cases that will guide future methodological advances. Overall, this program envisions a virtuous cycle of scientific discoveries that are both fueled by and transformative for an important sector of the Canadian economy.
Principal Investigators
Useful links
Resources related to this program will appear here.
Press review
Articles and interviews related to this program will appear here.
Call for postdoctoral project proposals
Program CLOSED
Recipients:
- Glen Berseth “Risk Sensitive Deep Reinforcement Learning for Planning in Uncertain Environments”
- Marie-Ève Rancourt “Data-driven network design for wildfire evacuation under uncertainty”
- Thibaut Vidal “Production Planning and Preemptive Maintenance: A Data-Driven Approach”
- Roussos Dimitrakopoulos “Smart Mineral Value/Supply Chains: Towards the Next Generation of Data-Driven, Lifelong Learning Stochastic Optimizers for Sustainable Mineral Resource Development”
Area of research: Integrated Machine Learning and Optimization for Decision Making under Uncertainty
Type of research: fundamental or applied
Type of program: support for postdoctoral fellows in research teams
Priority fields: data-driven optimization, contextual optimization, stochastic programming, robust optimization, supply chain applications
$35,000 for one year will be awarded to each selected project to provide partial support for a postdoctoral fellow in a research team. There is funding for a maximum of four projects. Projects can apply for a renewal after the first year.
Submission deadline: May 31st, 2022, 9 a.m. EDT.
Complete details for this call available in this PDF DOCUMENT.
NB: A SPECIAL SESSION of OPTIMIZATION DAYS 2022 (HEC Montréal, 16-18 May, 2022) will be dedicated to presenting and discussing this call for proposals and IVADO’s Strategic Research Program in Integrated Machine Learning and Optimization for Decision Making under Uncertainty.
Postdoctoral Positions
Multiple Postdoctoral Positions in Integrated Machine Learning and Optimization for Decision Making under Uncertainty at HEC Montréal/University of Montréal
Supervisors: Erick Delage (HEC Montréal, GERAD), Emma Frejinger (Université de Montréal, CIRRELT and Mila), Yossiri Adulyasak (HEC Montréal, GERAD), Pierre-Luc Bacon (Université de Montréal and Mila)
Duration: 1+1 (one-year contract with possible extension for the second year). The start date is flexible but it should ideally be before January 31, 2023.
Project description:
Postdoctoral researchers will work on fundamental or applied research supporting the IVADO Strategic Research Funding Program in Integrated Machine Learning and Optimization for Decision Making under Uncertainty (ML+Opt4DMU). The research program aims at developing new methods for making the most effective and adaptive use of data in decision‑making. It is founded on modern optimization and machine learning perspectives that encompass developments in, for example, deep reinforcement and end-to-end learning, risk‑averse decision theory, as well as contextual and distributionally robust optimization. The mission of ML+Opt4DMU is three-fold: (i) develop the next generation of methods to deal with uncertainty in data-driven risk-aware optimization models by integrating machine learning; (ii) identify scientifically challenging and high-impact opportunities for improving robustness in supply chains; and finally (iii) stimulate the integration of stochastic optimization models among our partners while defining use cases that will guide future methodological advances.
Requirements:
PhD in machine learning, applied mathematics, operations research, or related disciplines with a strong research record relevant to the ML+Opt4DMU research program.
How to apply:
Interested candidates are invited to submit (i) a CV, (ii) an electronic copy of all the university‑level transcripts, (iii) a short statement (approximately one page) describing their expertise, experience and research topics they would like to focus on under the ML+Opt4DMU research program, and (iv) contact details of 2-3 references (including their PhD supervisors). While all applications received by September 23, 2022 will be fully considered, those received after this date will continue to be considered until the positions are filled. All documents should be compiled into a single PDF file and sent to MLOpt4DMU@gmail.com. Applicants will be informed on the progress of the selection process only if they meet the aforementioned requirements.
In collaboration with
Contact
We encourage you to contact us for any additional information or questions related to this program. Please use this email and we will respond to you as soon as possible.