Pruning for efficient deterministic global optimization over trained ReLU neural networks
math.OC
Submitted: 2026-03-24
Updated: 2026-11-03
Code: https://github.com/ChemEngAI/ReLU_ANN_MILP
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Bounding and Counting Linear Regions of Deep Neural Networks
- DC3: A learning method for optimization with hard constraints
- ENFORCE: Nonlinear Constrained Learning with Adaptive-depth Neural Projection
- JANOS: An Integrated Predictive and Prescriptive Modeling Framework
- Mixed-Integer Optimization with Constraint Learning
- PySCIPOpt-ML: Embedding Trained Machine Learning Models into Mixed-Integer Programs
- Gaussian Error Linear Units (GELUs)
- When Deep Learning Meets Polyhedral Theory: A Survey
- Scaling Mixed-Integer Programming for Certification of Neural Network Controllers Using Bounds Tightening
- An analysis of optimization problems involving ReLU neural networks
- Learning both Weights and Connections for Efficient Neural Networks
- What is the State of Neural Network Pruning?
- Structured Pruning of Neural Networks for Constraints Learning
- Optimization over Trained (and Sparse) Neural Networks: A Surrogate within a Surrogate
- Comparing Rewinding and Fine-tuning in Neural Network Pruning
- Three Decades of Activations: A Comprehensive Survey of 400 Activation Functions for Neural Networks
- To prune, or not to prune: exploring the efficacy of pruning for model compression
- Rethinking the Value of Network Pruning
- Regularization for Deep Learning: A Taxonomy
- Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability
Related papers
- An Accelerated Proximal Gradient Method for Bures-Wasserstein Space
- FOMTools: Development and AI-Assisted Code Generation for First-Order Methods
- Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
- Dynamic Service Recommendation with Congestion-Dependent Joining: Near-Optimal and Constant-Factor Approximation Algorithms
- Integrating Learning and Optimization for Open Transport Capacity Pooling under Disruption
- Zeroth-Order Gradient Estimators under Decision-Dependent Noise