Piecewise linear neural networks and deep learning
As a powerful modelling method, piecewise linear neural networks (PWLNNs) have proven
successful in various fields, most recently in deep learning. To apply PWLNN methods, both …
successful in various fields, most recently in deep learning. To apply PWLNN methods, both …
Strong mixed-integer programming formulations for trained neural networks
We present strong mixed-integer programming (MIP) formulations for high-dimensional
piecewise linear functions that correspond to trained neural networks. These formulations …
piecewise linear functions that correspond to trained neural networks. These formulations …
The role of optimization in some recent advances in data-driven decision-making
Data-driven decision-making has garnered growing interest as a result of the increasing
availability of data in recent years. With that growth many opportunities and challenges have …
availability of data in recent years. With that growth many opportunities and challenges have …
ReLU networks as surrogate models in mixed-integer linear programs
B Grimstad, H Andersson - Computers & Chemical Engineering, 2019 - Elsevier
We consider the embedding of piecewise-linear deep neural networks (ReLU networks) as
surrogate models in mixed-integer linear programming (MILP) problems. A MILP formulation …
surrogate models in mixed-integer linear programming (MILP) problems. A MILP formulation …
When deep learning meets polyhedral theory: A survey
In the past decade, deep learning became the prevalent methodology for predictive
modeling thanks to the remarkable accuracy of deep neural networks in tasks such as …
modeling thanks to the remarkable accuracy of deep neural networks in tasks such as …
[HTML][HTML] Mixed-integer optimisation of graph neural networks for computer-aided molecular design
T McDonald, C Tsay, AM Schweidtmann… - Computers & Chemical …, 2024 - Elsevier
ReLU neural networks have been modelled as constraints in mixed integer linear
programming (MILP), enabling surrogate-based optimisation in various domains and …
programming (MILP), enabling surrogate-based optimisation in various domains and …
Lossless compression of deep neural networks
Deep neural networks have been successful in many predictive modeling tasks, such as
image and language recognition, where large neural networks are often used to obtain good …
image and language recognition, where large neural networks are often used to obtain good …
CAQL: Continuous action Q-learning
Value-based reinforcement learning (RL) methods like Q-learning have shown success in a
variety of domains. One challenge in applying Q-learning to continuous-action RL problems …
variety of domains. One challenge in applying Q-learning to continuous-action RL problems …
Empirical bounds on linear regions of deep rectifier networks
T Serra, S Ramalingam - Proceedings of the AAAI Conference on Artificial …, 2020 - aaai.org
We can compare the expressiveness of neural networks that use rectified linear units
(ReLUs) by the number of linear regions, which reflect the number of pieces of the piecewise …
(ReLUs) by the number of linear regions, which reflect the number of pieces of the piecewise …
Optimizing objective functions determined from random forests
We study the problem of optimizing a tree-based ensemble objective with the feasible
decisions lie in a polyhedral set. We model this optimization problem as a Mixed Integer …
decisions lie in a polyhedral set. We model this optimization problem as a Mixed Integer …