量子经典截断牛顿法求解高维能量景观
Quantum-classical truncated Newton method for high-dimensional energy landscapes
摘要:
我们开发了一个量子经典混合算法的函数优化,这是特别有用的神经网络的训练,因为它利用了高维能量景观的特定方面。由于最近将半监督学习公式化为优化问题,该算法可以进一步用于为深度生成模型找到最佳模型参数。特别是,我们提出了一种截断无鞍牛顿方法,该方法基于最近从优化、深度神经网络分析和随机矩阵理论中获得的见解。通过结合这些特定的量子子程序,我们能够用尽量子计算,以达到一个新的量子经典混合算法设计。我们的算法预计执行至少以及现有的经典算法,同时实现多项式加速。加速受到所需的经典读出的限制。从理论上讲,省略这个要求可以导致指数级的加速。
英文摘要:
We develop a quantum-classical hybrid algorithm for function optimization that is particularly useful in the training of neural networks since it makes use of particular aspects of high-dimensional energy landscapes. Due to a recent formulation of semi-supervised learning as an optimization problem, the algorithm can further be used to find the optimal model parameters for deep generative models. In particular, we present a truncated saddle-free Newton's method based on recent insight from optimization, analysis of deep neural networks and random matrix theory. By combining these with the specific quantum subroutines we are able to exhaust quantum computing in order to arrive at a new quantum-classical hybrid algorithm design. Our algorithm is expected to perform at least as well as existing classical algorithms while achieving a polynomial speedup. The speedup is limited by the required classical read-out. Omitting this requirement can in theory lead to an exponential speedup.
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。