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 2406.11889quant-phcs.AIcs.ET
收藏

超维量子因子分解

Hyperdimensional Quantum Factorization

Defense Advanced Research Projects Agency (DARPA)(美国国防高级研究计划局);University of California, Irvine(加利福尼亚大学欧文分校)

Prathyush Poduval, Zhuowen Zou, Alvaro Velasquez, Mohsen Imani

AI总结:

针对超维计算中超向量因子分解的经典方法成本过高的问题,提出量子算法HDQF,利用量子叠加编码潜在因子,实现相对经典搜索的二次加速,缓解容量瓶颈。

摘要:

本文提出一种可高效解码超向量的量子算法,解码是从超向量中提取原子元素的关键过程,也是超维计算(Hyperdimensional Computing, HDC)模型中用于可解释学习与信息检索的核心任务。HDC利用高维向量和高效算子对信息进行编码与操作,基于原子概念表示复杂对象。当尝试对由多个超向量乘积(绑定)得到的超向量进行解码时,基于经典优化的方法和专用循环网络的因子分解成本会高得难以承受,这是绑定操作的固有结果。我们提出HDQF这一创新量子计算方法来应对这一挑战。通过挖掘HDC与量子计算的相似性,并借助量子算法的加速能力,HDQF利用量子比特态和双极向量表示将潜在因子编码为量子叠加态。该方法相比经典搜索方法实现了二次加速,有效缓解了超向量因子分解的容量问题。

英文摘要:

This paper presents a quantum algorithm for efficiently decoding hypervectors, a crucial process in extracting atomic elements from hypervectors - an essential task in Hyperdimensional Computing (HDC) models for interpretable learning and information retrieval. HDC employs high-dimensional vectors and efficient operators to encode and manipulate information, representing complex objects from atomic concepts. When one attempts to decode a hypervector that is the product (binding) of multiple hypervectors, the factorization becomes prohibitively costly with classical optimization-based methods and specialized recurrent networks, an inherent consequence of the binding operation. We propose HDQF, an innovative quantum computing approach, to address this challenge. By exploiting parallels between HDC and quantum computing and capitalizing on quantum algorithms' speedup capabilities, HDQF encodes potential factors as a quantum superposition using qubit states and bipolar vector representation. This yields a quadratic speedup over classical search methods and effectively mitigates Hypervector Factorization capacity issues.

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。

↑