Training Safe Neural Networks with Global SDP Bounds
This advances reliable neural network verification for high-dimensional systems, potentially benefiting safe reinforcement learning policies.
The paper tackles the problem of training neural networks with formal safety guarantees by using semidefinite programming for verification, achieving provably perfect recall on the Adversarial Spheres dataset with input dimensions up to 40.
This paper presents a novel approach to training neural networks with formal safety guarantees using semidefinite programming (SDP) for verification. Our method focuses on verifying safety over large, high-dimensional input regions, addressing limitations of existing techniques that focus on adversarial robustness bounds. We introduce an ADMM-based training scheme for an accurate neural network classifier on the Adversarial Spheres dataset, achieving provably perfect recall with input dimensions up to $d=40$. This work advances the development of reliable neural network verification methods for high-dimensional systems, with potential applications in safe RL policies.