Learning Unitaries by Gradient Descent

01/31/2020
by   Bobak Toussi Kiani, et al.
0

We study the hardness of learning unitary transformations by performing gradient descent on the time parameters of sequences of alternating operators. Such sequences are the basis for the quantum approximate optimization algorithm and represent one of the simplest possible settings for investigating problems of controllability. In general, the loss function landscape of alternating operator sequences in U(d) is highly non-convex, and standard gradient descent can fail to converge to the global minimum in such spaces. In this work, we provide numerical evidence that – despite the highly non-convex nature of the control landscape – when the alternating operator sequence contains d^2 or more parameters, gradient descent always converges to the target unitary. The rates of convergence provide evidence for a "computational phase transition." When the number of parameters is less than d^2, gradient descent converges to a sub-optimal solution. When the number of parameters is greater than d^2, gradient descent converges rapidly and exponentially to an optimal solution. At the computational critical point where the number of parameters in the alternating operator sequence equals d^2, the rate of convergence is polynomial with a critical exponent of approximately 1.25.

READ FULL TEXT

page 4

page 7

research
11/03/2016

Finding Approximate Local Minima Faster than Gradient Descent

We design a non-convex second-order optimization algorithm that is guara...
research
10/31/2022

Almost Sure Convergence Rates of Stochastic Zeroth-order Gradient Descent for Łojasiewicz Functions

We prove almost sure convergence rates of Zeroth-order Gradient Descent ...
research
03/08/2021

Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem

In this paper we investigate how gradient-based algorithms such as gradi...
research
06/17/2022

Landscape Learning for Neural Network Inversion

Many machine learning methods operate by inverting a neural network at i...
research
11/04/2018

A Function Fitting Method

In this article we present a function fitting method, which is a convex ...
research
01/07/2020

Backtracking Gradient Descent allowing unbounded learning rates

In unconstrained optimisation on an Euclidean space, to prove convergenc...
research
06/01/2018

Run Procrustes, Run! On the convergence of accelerated Procrustes Flow

In this work, we present theoretical results on the convergence of non-c...

Please sign up or login with your details

Forgot password? Click here to reset