Optimizing quantum optimization algorithms via faster quantum gradient computation

by   András Gilyén, et al.

We consider a generic framework of optimization algorithms based on gradient descent. We develop a quantum algorithm that computes the gradient of a multi-variate real-valued function f:R^d→R by evaluating it at only a logarithmic number of points in superposition. Our algorithm is an improved version of Jordan's gradient calculation algorithm, providing an approximation of the gradient ∇ f with quadratically better dependence on the evaluation accuracy of f, for an important class of smooth functions. Furthermore, we show that most objective functions arising from quantum optimization procedures satisfy the necessary smoothness conditions, hence our algorithm provides a quadratic improvement in the complexity of computing their gradient. We also show that in a continuous phase-query model, our gradient computation algorithm has optimal query complexity up to poly-logarithmic factors, for a particular class of smooth functions. Moreover, we show that for low-degree multivariate polynomials our algorithm can provide exponential speedups compared to Jordan's algorithm in terms of the dimension d. One of the technical challenges in applying our gradient computation procedure for quantum optimization problems is the need to convert between a probability oracle (which is common in quantum optimization procedures) and a phase oracle (which is common in quantum algorithms) of the objective function f. We provide efficient subroutines to perform this delicate interconversion between the two types of oracles incurring only a logarithmic overhead, which might be of independent interest. Finally, using these tools we improve the runtime of prior approaches for training quantum auto-encoders, variational quantum eigensolvers, and quantum approximate optimization algorithms (QAOA).


page 1

page 2

page 3

page 4


Quantum Algorithms for Escaping from Saddle Points

We initiate the study of quantum algorithms for escaping from saddle poi...

Federated Optimization of Smooth Loss Functions

In this work, we study empirical risk minimization (ERM) within a federa...

Complexity of Highly Parallel Non-Smooth Convex Optimization

A landmark result of non-smooth convex optimization is that gradient des...

Policy Gradient based Quantum Approximate Optimization Algorithm

The quantum approximate optimization algorithm (QAOA), as a hybrid quant...

Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition

Stein Variational Gradient Descent (SVGD) is an important alternative to...

How to trap a gradient flow

We consider the problem of finding an ε-approximate stationary point of ...

Black-box Methods for Restoring Monotonicity

In many practical applications, heuristic or approximation algorithms ar...