GAMS Highlights GAMSPy at INFORMS Annual Meeting 2025
The INFORMS Annual Meeting 2025 in Atlanta was a productive and inspiring event for the GAMS team. Over five days, Steven Dirkse, Adam Christensen, Baudouin Brolet, and Maurice Jansen connected with academics, industry professionals, and software developers to showcase the latest innovations around GAMSPy.
Focus on GAMSPy
GAMSPy drew strong attention throughout the conference. Steve and Adam led an introductory workshop and two follow-up sessions that sparked lively discussions about modeling and migration from GAMS to GAMSPy. The positive response confirmed growing momentum around our Python-based modeling environment.
Booth Activity and Academic Interest
The GAMS booth quickly became a hub for professors, researchers, and students interested in GAMSPy. Many were excited to learn that it’s free for academic use, resulting in a strong wave of new sign-ups for our academic program.
Industry and Community Connections
Alongside academic engagement, we connected with potential commercial partners such as Aramco and Home Depot, strengthening our pipeline of future collaborations. The exhibition also featured other major players in the field, with NVIDIA’s COIN-OR Cup win for cuOpt highlighting the community’s strong focus on high-performance computing.
A Great Experience in Atlanta
Beyond the professional success, the team enjoyed exploring Atlanta together, guided by Adam - from visits to Georgia Tech to their first hands-on experience with a Waymo driverless car.
The 2025 meeting reaffirmed GAMS’s active role in the optimization community and inspired new ideas and connections for the year ahead.
Sign up for our general information newsletter to stay up-to-date!
Our Abstracts
Pre-conference Workshop:
An Introduction to Modeling with GAMSPy
Presented by: Adam Christensen
This workshop offers a hands-on introduction to GAMSPy. GAMSPy combines the high-performance GAMS execution system with the flexible Python language, creating a powerful mathematical optimization package. It acts as a bridge between the expressive Python language and the robust GAMS system, allowing you to effortlessly create complex mathematical models and applications.
Join us to explore GAMSPy’s fundamental functionalities through practical, interactive exercises. We’ll cover everything from defining sets, parameters, variables, and equations to solving models and retrieving results, all within a familiar Python environment. Beyond the basics, we’ll also provide a glimpse into more advanced features, demonstrating how GAMSPy can streamline complex modeling workflows and enhance your analytical capabilities.
Whether you’re a seasoned GAMS user looking to integrate with Python or a Python user curious about optimization, this workshop will equip you with essential skills needed to get started and demonstrate what is possible with GAMSPy.
Exhibitor Technology Showcases
Mathematical programs with embedded surrogate models using GAMSPy
Presented by: Adam Christensen
Recent advances in ML/AI have commoditized the development of surrogate models using tools such as PyTorch, Scikit-Learn, and TensorFlow. These surrogate models simplify inherently non-linear phenomena, approximating complex behaviors so they can serve as constraints in optimization frameworks. Embedding these models in algebraic modeling languages (AMLs) like GAMS remains challenging: designed for sparse algebra, AMLs lack seamless integration with third-party software. The rise of Python in data science has motivated a paradigm shift, inspiring tools that bridge classical AMLs and current computational techniques.
We introduce GAMSPy, a native Python AML combining the mathematical transparency and scalability of traditional AMLs with Python’s ecosystem. Its set-driven constructs and operator overloading preserve the syntax of handwritten algebra while supporting dense matrix operations—matrix multiplication, transposition, norms—essential to ML/AI. While the GAMS “classic” engine excels at indexed algebra, GAMSPy extends its capabilities to accommodate ML workflows.
We demonstrate embedding a neural network trained in PyTorch to model an energy system as a constraint within an optimization problem, enabling system engineers to optimize plant operations with detailed energy conversion models. This workflow exemplifies applications spanning weather forecasting and market behavior modeling. We also compare GAMSPy to existing approaches, discuss future developments, and highlight innovative intersections of mathematical modeling and machine learning.
GAMSPy represents a significant convergence of AML rigor and Python-driven ML versatility. Its design prioritizes computational efficiency, syntactic clarity, and scalability, offering a robust platform that overcomes integration hurdles and unlocks new possibilities at the intersection of optimization and data science.
An Introduction to Modeling with GAMSPy
Presented by: Adam Christensen & Steven Dirkse
Our showcase offers a hands-on introduction to GAMSPy. GAMSPy combines the high-performance GAMS execution system with the flexible Python language, creating a powerful mathematical optimization package. It acts as a bridge between the expressive Python language and the robust GAMS system, allowing you to effortlessly create complex mathematical models and applications.
Join us to explore GAMSPy’s fundamental functionalities through practical, interactive exercises. We’ll cover everything from defining sets, parameters, variables, and equations to solving models and retrieving results, all within a familiar Python environment. Beyond the basics, we’ll also provide a glimpse into more advanced features, demonstrating how GAMSPy can streamline complex modeling workflows and enhance your analytical capabilities.
Whether you’re a seasoned GAMS user looking to integrate with Python or a Python user curious about optimization, this workshop will equip you with essential skills needed to get started and demonstrate what is possible with GAMSPy.
Check our presentation slides for more information:
| Name: | Size / byte: | |
|---|---|---|
| 2042503 |
