LAWS: Look Around and Warm-Start Natural Gradient Descent for Quantum Neural Networks

05/05/2022
by   Zeyi Tao, et al.
0

Variational quantum algorithms (VQAs) have recently received significant attention from the research community due to their promising performance in Noisy Intermediate-Scale Quantum computers (NISQ). However, VQAs run on parameterized quantum circuits (PQC) with randomly initialized parameters are characterized by barren plateaus (BP) where the gradient vanishes exponentially in the number of qubits. In this paper, we first review quantum natural gradient (QNG), which is one of the most popular algorithms used in VQA, from the classical first-order optimization point of view. Then, we proposed a Look Around Warm-Start QNG (LAWS) algorithm to mitigate the widespread existing BP issues. LAWS is a combinatorial optimization strategy taking advantage of model parameter initialization and fast convergence of QNG. LAWS repeatedly reinitializes parameter search space for the next iteration parameter update. The reinitialized parameter search space is carefully chosen by sampling the gradient close to the current optimal. Moreover, we present a unified framework (WS-SGD) for integrating parameter initialization techniques into the optimizer. We provide the convergence proof of the proposed framework for both convex and non-convex objective functions based on Polyak-Lojasiewicz (PL) condition. Our experiment results show that the proposed algorithm could mitigate the BP and have better generalization ability in quantum classification problems.

READ FULL TEXT

page 1

page 10

research
05/26/2022

Avoiding Barren Plateaus with Classical Deep Neural Networks

Variational quantum algorithms (VQAs) are among the most promising algor...
research
02/02/2021

Capacity and quantum geometry of parametrized quantum circuits

To harness the potential of noisy intermediate-scale quantum devices, it...
research
04/29/2021

Optimal training of variational quantum algorithms without barren plateaus

Variational quantum algorithms (VQAs) promise efficient use of near-term...
research
02/25/2022

CAFQA: Clifford Ansatz For Quantum Accuracy

Variational Quantum Algorithms (VQAs) rely upon the iterative optimizati...
research
09/23/2022

Error Mitigation-Aided Optimization of Parameterized Quantum Circuits: Convergence Analysis

Variational quantum algorithms (VQAs) offer the most promising path to o...
research
12/24/2020

AsymptoticNG: A regularized natural gradient optimization algorithm with look-ahead strategy

Optimizers that further adjust the scale of gradient, such as Adam, Natu...
research
08/06/2023

Enabling High Performance Debugging for Variational Quantum Algorithms using Compressed Sensing

Variational quantum algorithms (VQAs) can potentially solve practical pr...

Please sign up or login with your details

Forgot password? Click here to reset