WEBINAR / EVENT
Optimization Over Trained Neural Networks: Taking a Relaxing Walk
Besides training, mathematical optimization is also used in deep learning to model and solve formulations over trained neural networks for purposes such as verification, compression, and optimization with learned constraints.
August 28, 2024
WEBINAR / EVENT
Optimization Over Trained Neural Networks: Taking a Relaxing Walk
Besides training, mathematical optimization is also used in deep learning to model and solve formulations over trained neural networks for purposes such as verification, compression, and optimization with learned constraints.
August 28, 2024
WEBINAR / EVENT
Optimization Over Trained Neural Networks: Taking a Relaxing Walk
Besides training, mathematical optimization is also used in deep learning to model and solve formulations over trained neural networks for purposes such as verification, compression, and optimization with learned constraints.
August 28, 2024
August 28, 2024 at 11 AM EDT
Besides training, mathematical optimization is also used in deep learning to model and solve formulations over trained neural networks for purposes such as verification, compression, and optimization with learned constraints. However, solving these formulations soon becomes difficult as the network size grows due to the weak linear relaxation and dense constraint matrix. We have seen improvements in recent years with cutting plane algorithms, reformulations, and a heuristic based on Mixed-Integer Linear Programming (MILP).
Join Dr. Thiago Serra for this webinar where he proposes a more scalable heuristic based on exploring global and local linear relaxations of the neural network model.
August 28, 2024 at 11 AM EDT
Besides training, mathematical optimization is also used in deep learning to model and solve formulations over trained neural networks for purposes such as verification, compression, and optimization with learned constraints. However, solving these formulations soon becomes difficult as the network size grows due to the weak linear relaxation and dense constraint matrix. We have seen improvements in recent years with cutting plane algorithms, reformulations, and a heuristic based on Mixed-Integer Linear Programming (MILP).
Join Dr. Thiago Serra for this webinar where he proposes a more scalable heuristic based on exploring global and local linear relaxations of the neural network model.
August 28, 2024 at 11 AM EDT
Besides training, mathematical optimization is also used in deep learning to model and solve formulations over trained neural networks for purposes such as verification, compression, and optimization with learned constraints. However, solving these formulations soon becomes difficult as the network size grows due to the weak linear relaxation and dense constraint matrix. We have seen improvements in recent years with cutting plane algorithms, reformulations, and a heuristic based on Mixed-Integer Linear Programming (MILP).
Join Dr. Thiago Serra for this webinar where he proposes a more scalable heuristic based on exploring global and local linear relaxations of the neural network model.
Speakers
Meet Your Expert Speaker
Learn from the best in the industry, bringing years of experience and groundbreaking insights to the forefront of AI personalization.
Thiago Serra
Assistant Professor of Business Analytics
Thiago Serra is an Assistant Professor of Business Analytics at the University of Iowa and a consultant for Mitsubishi Electric Research Labs. His scholarship focuses on the theory, practice, and integration of machine learning and mathematical optimization. Previously, he was an assistant professor at Bucknell University, a visiting research scientist at Mitsubishi Electric Research Labs, and an operations research analyst at Petrobras. He has a Ph.D. in operations research from Carnegie Mellon University, from which he received the Gerald L. Thompson Doctoral Dissertation Award in Management Science. He also has a master's degree in computer science from the University of Sao Paulo (USP) and a computer engineering degree from the University of Campinas (Unicamp). He has served the INFORMS Computing Society as vice chair (2022-2023) and chair (2024-2025). He currently serves as an associate editor for the journals International Transactions in Operational Research and INFORMS Journal on Data Science.
Speakers
Meet Your Expert Speaker
Learn from the best in the industry, bringing years of experience and groundbreaking insights to the forefront of AI personalization.
Thiago Serra
Assistant Professor of Business Analytics
Thiago Serra is an Assistant Professor of Business Analytics at the University of Iowa and a consultant for Mitsubishi Electric Research Labs. His scholarship focuses on the theory, practice, and integration of machine learning and mathematical optimization. Previously, he was an assistant professor at Bucknell University, a visiting research scientist at Mitsubishi Electric Research Labs, and an operations research analyst at Petrobras. He has a Ph.D. in operations research from Carnegie Mellon University, from which he received the Gerald L. Thompson Doctoral Dissertation Award in Management Science. He also has a master's degree in computer science from the University of Sao Paulo (USP) and a computer engineering degree from the University of Campinas (Unicamp). He has served the INFORMS Computing Society as vice chair (2022-2023) and chair (2024-2025). He currently serves as an associate editor for the journals International Transactions in Operational Research and INFORMS Journal on Data Science.
Speakers
Meet Your Expert Speaker
Learn from the best in the industry, bringing years of experience and groundbreaking insights to the forefront of AI personalization.
Assistant Professor of Business Analytics
Thiago Serra
Thiago Serra is an Assistant Professor of Business Analytics at the University of Iowa and a consultant for Mitsubishi Electric Research Labs. His scholarship focuses on the theory, practice, and integration of machine learning and mathematical optimization. Previously, he was an assistant professor at Bucknell University, a visiting research scientist at Mitsubishi Electric Research Labs, and an operations research analyst at Petrobras. He has a Ph.D. in operations research from Carnegie Mellon University, from which he received the Gerald L. Thompson Doctoral Dissertation Award in Management Science. He also has a master's degree in computer science from the University of Sao Paulo (USP) and a computer engineering degree from the University of Campinas (Unicamp). He has served the INFORMS Computing Society as vice chair (2022-2023) and chair (2024-2025). He currently serves as an associate editor for the journals International Transactions in Operational Research and INFORMS Journal on Data Science.
