论文标题
NOVA：通过自适应随机搜索端到端学习和控制的非凸优化
NOVAS: Non-convex Optimization via Adaptive Stochastic Search for End-to-End Learning and Control
论文作者
论文摘要
在这项工作中，我们建议将自适应随机搜索用作深度神经网络体系结构中一般非凸优化操作的基础。具体而言，对于位于网络中某个层的目标函数并通过某些网络参数进行参数化，我们采用自适应随机搜索来对其输出进行优化。该操作是可区分的，并且不会阻碍逆转过程中梯度的传递，从而使我们能够将其作为端到端学习中的组成部分。我们研究了提出的优化模块的属性，并根据基于合成能量的结构化预测任务进行了针对两种现有替代方案的基准测试，并进一步展示了其在随机最佳控制应用中的使用。
In this work we propose the use of adaptive stochastic search as a building block for general, non-convex optimization operations within deep neural network architectures. Specifically, for an objective function located at some layer in the network and parameterized by some network parameters, we employ adaptive stochastic search to perform optimization over its output. This operation is differentiable and does not obstruct the passing of gradients during backpropagation, thus enabling us to incorporate it as a component in end-to-end learning. We study the proposed optimization module's properties and benchmark it against two existing alternatives on a synthetic energy-based structured prediction task, and further showcase its use in stochastic optimal control applications.
