arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1609.07152cs.LGmath.OC
收藏

输入凸神经网络

Input Convex Neural Networks

Carnegie Mellon University(卡内基梅隆大学);Tsinghua University(清华大学)

Brandon Amos, Lei Xu, J. Zico Kolter

摘要:

本文提出了输入凸神经网络体系结构。这些是标量值(潜在深度)神经网络,对网络参数有约束,使得网络的输出是(一些)输入的凸函数。该网络允许通过对网络的一些输入进行优化来进行有效的推理,并且可以应用于包括结构化预测、数据填补、强化学习等的设置。在本文中,我们为这些模型奠定了基础,提出了推理,优化和学习的方法,并分析了它们的代表性。我们表明,许多现有的神经网络架构可以作出微小的修改,输入凸,并开发专门的优化算法,以适应这种设置。最后,我们强调了这些方法在多标签预测,图像完成和强化学习问题上的性能,在许多情况下,我们显示了对现有技术的改进。

英文摘要:

This paper presents the input convex neural network architecture. These are scalar-valued (potentially deep) neural networks with constraints on the network parameters such that the output of the network is a convex function of (some of) the inputs. The networks allow for efficient inference via optimization over some inputs to the network given others, and can be applied to settings including structured prediction, data imputation, reinforcement learning, and others. In this paper we lay the basic groundwork for these models, proposing methods for inference, optimization and learning, and analyze their representational power. We show that many existing neural network architectures can be made input-convex with a minor modification, and develop specialized optimization algorithms tailored to this setting. Finally, we highlight the performance of the methods on multi-label prediction, image completion, and reinforcement learning problems, where we show improvement over the existing state of the art in many cases.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑