Quantum Algorithms for Escaping from Saddle Points

07/20/2020
by   Chenyi Zhang, et al.
0

We initiate the study of quantum algorithms for escaping from saddle points with provable guarantee. Given a function fℝ^n→ℝ, our quantum algorithm outputs an ϵ-approximate second-order stationary point using Õ(log^2 n/ϵ^1.75) queries to the quantum evaluation oracle (i.e., the zeroth-order oracle). Compared to the classical state-of-the-art algorithm by Jin et al. with Õ(log^6 n/ϵ^1.75) queries to the gradient oracle (i.e., the first-order oracle), our quantum algorithm is polynomially better in terms of n and matches its complexity in terms of 1/ϵ. Our quantum algorithm is built upon two techniques: First, we replace the classical perturbations in gradient descent methods by simulating quantum wave equations, which constitutes the polynomial speedup in n for escaping from saddle points. Second, we show how to use a quantum gradient computation algorithm due to Jordan to replace the classical gradient queries by quantum evaluation queries with the same complexity. Finally, we also perform numerical experiments that support our quantum speedup.

READ FULL TEXT
research
11/28/2021

Escape saddle points by a simple gradient-descent based algorithm

Escaping saddle points is a central research topic in nonconvex optimiza...
research
12/05/2022

Robustness of Quantum Algorithms for Nonconvex Optimization

Recent results suggest that quantum computers possess the potential to s...
research
06/21/2023

Quantum and classical query complexities for determining connectedness of matroids

Connectivity is a fundamental structural property of matroids, and has b...
research
11/01/2017

Optimizing quantum optimization algorithms via faster quantum gradient computation

We consider a generic framework of optimization algorithms based on grad...
research
12/03/2021

Classical computation of quantum guesswork

The guesswork quantifies the minimum number of queries needed to guess t...
research
11/17/2020

Quantum algorithms for learning graphs and beyond

We study the problem of learning an unknown graph provided via an oracle...
research
04/14/2020

Quantum speedups of some general-purpose numerical optimisation algorithms

We give quantum speedups of several general-purpose numerical optimisati...

Please sign up or login with your details

Forgot password? Click here to reset