SuperEncoder: Towards Iteration-Free Approximate Quantum State Preparation

Yilun Zhao, Bingmeng Wang, Wenle Jiang, Xiwei Pan, Bing Li, Yinhe Han, ying wang

Keywords: Quantum Computing

TL;DR: Utilizing a classical neural network to directly generate parameters of a structured quantum circuit to prepare any target quantum state

Abstract: Numerous quantum algorithms operate under the assumption that classical data has already been converted into quantum states, a process termed Quantum State Preparation (QSP). However, achieving precise QSP requires a circuit depth that scales exponentially with the number of qubits, making it a substantial obstacle in harnessing quantum advantage. Recent research suggests using a Parameterized Quantum Circuit (PQC) to approximate a target state, offering a more scalable solution with reduced circuit depth compared to precise QSP. Despite this, the need for iterative updates of circuit parameters results in a lengthy runtime, limiting its practical application. To overcome this challenge, we introduce SuperEncoder, a pre-trained classical neural network model designed to directly estimate the parameters of a PQC for any given quantum state. By eliminating the need for iterative parameter tuning, SuperEncoder represents a pioneering step towards iteration-free approximate QSP.

Primary Area: Machine learning for other sciences and fields

Submission Number: 241