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 2006.01013quant-phcs.LG
收藏

在线量子态学习的实用自适应算法

More Practical and Adaptive Algorithms for Online Quantum State Learning

Institute for Quantum Computing(量子计算研究所);Baidu Research(百度研究院)

Yifang Chen, Xin Wang

摘要:

在线量子态学习是Aaronson等人(2018)最近提出的一个问题,其中学习者基于给定的状态测量和噪声结果顺序预测$n$ -量子比特量子态。在以前的工作中,算法一般是最坏情况下的最优,但在某些更简单或更实际的情况下,无法实现更严格的界限。在本文中,我们开发的算法,以提高在线学习的量子态。首先,我们证明了具有Tallis-2熵的正则化跟随领导者(RFTL)方法可以在具有最大秩$M$的第一个$T$测量上实现具有完美后见之明的$O(\sqrt{MT})$总损失。该遗憾界限仅取决于测量的最大秩$M$而不是量子比特的数量,这利用了低秩测量。其次,我们提出了一个无参数算法的基础上,经典的调整学习率时间表,可以实现一个遗憾,这取决于损失的最佳状态,在事后诸葛亮,它利用低噪声的结果。除了这些更自适应的界限,我们还表明,我们的RFTL与Tallis-2熵算法可以有效地实现在近期的量子计算设备,这是不能实现在以前的作品。

英文摘要:

Online quantum state learning is a recently proposed problem by Aaronson et al. (2018), where the learner sequentially predicts $n$-qubit quantum states based on given measurements on states and noisy outcomes. In the previous work, the algorithms are worst-case optimal in general but fail in achieving tighter bounds in certain simpler or more practical cases. In this paper, we develop algorithms to advance the online learning of quantum states. First, we show that Regularized Follow-the-Leader (RFTL) method with Tallis-2 entropy can achieve an $O(\sqrt{MT})$ total loss with perfect hindsight on the first $T$ measurements with maximum rank $M$. This regret bound depends only on the maximum rank $M$ of measurements rather than the number of qubits, which takes advantage of low-rank measurements. Second, we propose a parameter-free algorithm based on a classical adjusting learning rate schedule that can achieve a regret depending on the loss of best states in hindsight, which takes advantage of low noisy outcomes. Besides these more adaptive bounds, we also show that our RFTL with Tallis-2 entropy algorithm can be implemented efficiently on near-term quantum computing devices, which is not achievable in previous works.

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。

↑