A paradigmatic algorithm for online learning is the Hedge algorithm by Freund and Schapire. An allocation into different strategies is chosen for multiple rounds and each round incurs corresponding losses for each strategy. The algorithm obtains a favorable guarantee for the total losses even in an adversarial situation. This work presents quantum algorithms for such online learning in an oracular setting. For $T$ time steps and $N$ strategies, we exhibit run times of about $O \left ({\rm poly} (T) \sqrt{N} \right)$ for estimating the losses and for betting on individual strategies by sampling. In addition, we discuss a quantum analogue of the Sparsitron, a machine learning algorithm based on the Hedge algorithm. The quantum algorithm inherits the provable learning guarantees from the classical algorithm and exhibits polynomial speedups. The speedups may find relevance in finance, for example for hedging risks, and machine learning, for example for learning generalized linear models or Ising models.
High-Fidelity Universal Quantum Gate Compilation for Non-semisimple Ising Anyons via Genetic Algorithm-Optimized Solovay-Kitaev Decomposition
School of Physics and Optoelectronics, Xiangtan University(湘潭大学物理与光电工程学院);School of Physics and Electronic Science, Hunan Institute of Science and Technology(湖南理工学院物理与电子科学学院);Center for Quantum Science and Technology, Department of Physics, Shanghai University(上海大学物理学部量子科学与技术中心)
Enumeration algorithms for combinatorial problems using Ising machines: When should we stop exploring energy landscapes?
Research Institute for Electronic Science, Hokkaido University(北海道大学电子科学研究所);Institute for Chemical Reaction Design and Discovery (WPI-ICReDD), Hokkaido University(北海道大学化学反应设计与发现研究所(WPI-ICReDD));Graduate School of Chemical Sciences and Engineering, Hokkaido University(北海道大学理工研究院);Statistics Discipline, Khulna University(库尔纳大学统计学系);SANKEN, The University of Osaka(大阪大学基础工学研究所)
A quantum algorithm for additive approximation of Ising partition functions
研究了计算伊辛模型的配分函数的量子计算复杂性。我们构造了一个量子算法,用于平方格上Ising配分函数的加性近似。为此,我们利用Van den Nest、Dür和Briegel [Phys. Rev. Lett. 98,117207(2007)]及其通过基于测量的量子计算(MBQC)的解释。我们指定一个算法域,所提出的算法的工作原理,和近似规模,这决定了近似的精度。我们表明,所提出的算法做了一个非平凡的任务,这将是棘手的任何经典计算机,通过显示所提出的量子算法可解决的问题是BQP-完全的。在构造BQP完备问题时,耦合强度和磁场取复值。然而,统计物理学和计算机科学的核心兴趣伊辛模型由真实的耦合强度和磁场组成。因此,我们将所提出的算法的算法域扩展到这样一个真实的物理参数区域,并显式地计算近似尺度。我们发现,重叠映射及其MBQC解释提高了近似规模指数相比,一个简单的恒定深度量子算法。另一方面,该量子算法也为我们提供了一个部分的证据,证明即使在正方形格点上也不存在有效的经典算法来计算Ising配分函数的乘法近似.这一结果支持了所提出的量子算法在物理参数区域也做了非平凡的任务。