GEAR: A GPU-Accelerated Global Solver for Bounded Continuous Nonlinear Programs via Linear Bound Propagation
math.OC, cs.LG, cs.MS, cs.NA, math.NA
Submitted: 2026-11-07
Updated: 2026-11-07
Project page: https://verified-intelligence.github.io/GEAR
Terminology
Sources
- PDLP: A Practical First-Order Method for Large-Scale Linear Programming
- Verification-Aided Learning of Neural Network Barrier Functions with Termination Guarantees
- Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition
- Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound
- Deep Neural Networks as 0-1 Mixed Integer Linear Programs: A Feasibility Study
- When Deep Learning Meets Polyhedral Theory: A Survey
- Neural Network Branching for Neural Network Verification
- Evaluating Robustness of Neural Networks with Mixed Integer Programming
- Accelerating Deterministic Global Optimization via GPU-parallel Interval Arithmetic
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