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 2006.14904quant-phcs.LG
收藏

量子神经网络的分层学习

Layerwise learning for quantum neural networks

Volkswagen Data:Lab(大众数据实验室);Ludwig Maximilian University(路德维希·马克西米利安大学);Leiden University(莱顿大学);Google Research(谷歌研究院);Volkswagen Group Machine Learning Research Lab(大众集团机器学习研究实验室);Eötvös Loránd University(厄特沃什·罗兰大学)

Andrea Skolik, Jarrod R. McClean, Masoud Mohseni, Patrick van der Smagt, Martin Leib

摘要:

随着对量子电路学习在量子设备上的近期应用的关注增加,结合由参数化量子线路的成本函数景观提出的独特挑战,有效训练的策略变得越来越重要。为了改善这些挑战中的一些,我们研究了参数化量子线路的分层学习策略。电路深度在优化过程中逐渐增加,并且在每个训练步骤中仅更新参数的子集。我们表明,当考虑采样噪声时,这种策略可以帮助避免由于电路深度低,一步训练的参数数量少,以及与训练整个电路相比梯度幅度较大而导致的错误表面的贫瘠高原问题。这些特性使我们的算法更适合在嘈杂的中等规模量子设备上执行。我们展示了我们的方法对手写数字的图像分类任务,并表明,分层学习达到了8%的平均泛化误差相比,标准的学习计划,用于训练相同大小的量子线路。此外,与训练整个电路相比,达到较低测试误差的运行百分比最多高达40%,而整个电路在训练期间很容易进入平台期。

英文摘要:

With the increased focus on quantum circuit learning for near-term applications on quantum devices, in conjunction with unique challenges presented by cost function landscapes of parametrized quantum circuits, strategies for effective training are becoming increasingly important. In order to ameliorate some of these challenges, we investigate a layerwise learning strategy for parametrized quantum circuits. The circuit depth is incrementally grown during optimization, and only subsets of parameters are updated in each training step. We show that when considering sampling noise, this strategy can help avoid the problem of barren plateaus of the error surface due to the low depth of circuits, low number of parameters trained in one step, and larger magnitude of gradients compared to training the full circuit. These properties make our algorithm preferable for execution on noisy intermediate-scale quantum devices. We demonstrate our approach on an image-classification task on handwritten digits, and show that layerwise learning attains an 8% lower generalization error on average in comparison to standard learning schemes for training quantum circuits of the same size. Additionally, the percentage of runs that reach lower test errors is up to 40% larger compared to training the full circuit, which is susceptible to creeping onto a plateau during training.

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。

↑