论文标题
半决赛约束下的神经网络培训
Neural network training under semidefinite constraints
论文作者
论文摘要
本文涉及在半决赛约束下对神经网络（NNS）的培训，该培训允许使用稳健性和稳定性保证进行NN培训。特别是，我们专注于Lipschitz的NNS界限。利用基础矩阵约束的带状结构，我们基于内部方法为此类训练问题设置了一个有效且可扩展的训练方案。我们的实施使Lipschitz的限制在大规模深入的训练中（例如Wasserstein生成对抗网络（WGAN））通过半限制约束。在数值示例中，我们显示了我们方法的优越性及其对wgan培训的适用性。
This paper is concerned with the training of neural networks (NNs) under semidefinite constraints, which allows for NN training with robustness and stability guarantees. In particular, we focus on Lipschitz bounds for NNs. Exploiting the banded structure of the underlying matrix constraint, we set up an efficient and scalable training scheme for NN training problems of this kind based on interior point methods. Our implementation allows to enforce Lipschitz constraints in the training of large-scale deep NNs such as Wasserstein generative adversarial networks (WGANs) via semidefinite constraints. In numerical examples, we show the superiority of our method and its applicability to WGAN training.
