通过VB-FTRL以对数损失在线学习量子态
Online Learning Quantum States with the Logarithmic Loss via VB-FTRL
AI总结:
本文将VB-FTRL算法推广至以对数损失在线学习量子态(LL-OLQS)问题,实现$O(d^2/log(d+T))$的遗憾率,迭代可多项式时间求解,还引入VB-凸性概念,优于现有指数权重法的遗憾率且有显式实现。
摘要:
以对数损失在线学习量子态(LL-OLQS)是在线投资组合选择(OPS)的量子推广,OPS是在线学习领域三十多年来的经典开放问题。该问题也出现在设计最大似然量子态层析成像的随机优化算法中。最近,Jezequel等人(arXiv:2209.13932)提出了VB-FTRL算法,这是首个计算复杂度适中且遗憾最优的OPS算法。本文将VB-FTRL推广至LL-OLQS。设$d$表示维度,$T$表示轮数,推广后的算法对LL-OLQS实现了$O(d^2/log(d+T))$的遗憾率。算法的每次迭代需求解半定规划,可通过切割平面法等在多项式时间内实现。作为对比,LL-OLQS目前已知的最优遗憾率为$O(d^2/log T)$,由指数权重法实现,但该方法尚无针对LL-OLQS的显式实现。为促进推广,我们引入VB-凸性的概念,它是任意函数的体积障碍为凸的充分条件,具有独立研究价值。
英文摘要:
Online learning of quantum states with the logarithmic loss (LL-OLQS) is a quantum generalization of online portfolio selection (OPS), a classic open problem in online learning for over three decades. This problem also emerges in designing stochastic optimization algorithms for maximum-likelihood quantum state tomography. Recently, Jezequel et al. (arXiv:2209.13932) proposed the VB-FTRL algorithm, the first regret-optimal algorithm for OPS with moderate computational complexity. In this paper, we generalize VB-FTRL for LL-OLQS. Let $d$ denote the dimension and $T$ the number of rounds. The generalized algorithm achieves a regret rate of $O ( d^2 \log ( d + T ) )$ for LL-OLQS. Each iteration of the algorithm consists of solving a semidefinite program that can be implemented in polynomial time by, for example, cutting-plane methods. For comparison, the best-known regret rate for LL-OLQS is currently $O ( d^2 \log T )$, achieved by an exponential weight method. However, no explicit implementation is available for the exponential weight method for LL-OLQS. To facilitate the generalization, we introduce the notion of VB-convexity. VB-convexity is a sufficient condition for the volumetric barrier associated with any function to be convex and is of independent interest.
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。