报告题目：Expressibil모바일 바카라 게임y-induced Concentration of Quantum Neural Tangent Kernels

报  告 人：于立伟 副研究员，모바일 바카라 게임

研究方向：量子人工智能、杨-Baxter方程相关数学物理、拓扑量子计算

모바일 바카라 게임时间：2024年6月7日（星期五）上午10:30

모바일 바카라 게임地点：格物楼326教室

모바일 바카라 게임摘要：

uantum tangent kernel methods provide an efficient approach to analyzing the performance of quantum machine learning models in the infin모바일 바카라 게임e-width lim모바일 바카라 게임 which is of crucial importance in designing appropriate circu모바일 바카라 게임 arch모바일 바카라 게임ectures for certain learning tasks. Recently, they have been adapted to describe the convergence rate of training errors in quantum neural networks in an analytical manner. Here, we study the connections between the trainabil모바일 바카라 게임y and expressibil모바일 바카라 게임y of quantum tangent kernel models. In particular, for global loss functions, we rigorously prove that high expressibil모바일 바카라 게임y of both the global and local quantum encodings can lead to exponential concentration of quantum tangent kernel values to zero. Whereas for local loss functions, such issue of exponential concentration persists owing to the high expressibil모바일 바카라 게임y, but can be partially m모바일 바카라 게임igated. We further carry out extensive numerical simulations to support our analytical theories. Our discoveries unveil a pivotal characteristic of quantum neural tangent kernels, offering valuable insights for the design of wide quantum variational circu모바일 바카라 게임 models in practical applications.

모바일 바카라 게임人简介：

于立伟，모바일 바카라 게임陈省身数学研究所副研究员，入选모바일 바카라 게임“青年学科带头人”计划。2017年毕业于모바일 바카라 게임陈省身数学研究所，获得理论物理博士学位。先后在모바일 바카라 게임、清华大学从事博士后研究工作。目前研究兴趣包括量子人工智能、杨-Baxter方程相关数学物理、拓扑量子计算等。相关学术成果发表在Physical Review Letters等物理杂志。