The power of quantum neural networks

10/30/2020
by   Amira Abbas, et al.
183

Fault-tolerant quantum computers offer the promise of dramatically improving machine learning through speed-ups in computation or improved model scalability. In the near-term, however, the benefits of quantum machine learning are not so clear. Understanding expressibility and trainability of quantum models-and quantum neural networks in particular-requires further investigation. In this work, we use tools from information geometry to define a notion of expressibility for quantum and classical models. The effective dimension, which depends on the Fisher information, is used to prove a novel generalisation bound and establish a robust measure of expressibility. We show that quantum neural networks are able to achieve a significantly better effective dimension than comparable classical neural networks. To then assess the trainability of quantum models, we connect the Fisher information spectrum to barren plateaus, the problem of vanishing gradients. Importantly, certain quantum neural networks can show resilience to this phenomenon and train faster than classical models due to their favourable optimisation landscapes, captured by a more evenly spread Fisher information spectrum. Our work is the first to demonstrate that well-designed quantum neural networks offer an advantage over classical neural networks through a higher effective dimension and faster training ability, which we verify on real quantum hardware.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/20/2022

Variational Quantum Policy Gradients with an Application to Quantum Control

Quantum Machine Learning models are composed by Variational Quantum Circ...
research
11/03/2020

Power of data in quantum machine learning

The use of quantum computing for machine learning is among the most exci...
research
02/10/2023

Effects of noise on the overparametrization of quantum neural networks

Overparametrization is one of the most surprising and notorious phenomen...
research
01/29/2020

A scale-dependent notion of effective dimension

We introduce a notion of "effective dimension" of a statistical model ba...
research
05/30/2023

Quantum Convolutional Neural Networks for Multi-Channel Supervised Learning

As the rapidly evolving field of machine learning continues to produce i...
research
06/09/2021

The dilemma of quantum neural networks

The core of quantum machine learning is to devise quantum models with go...
research
05/22/2023

On quantum backpropagation, information reuse, and cheating measurement collapse

The success of modern deep learning hinges on the ability to train neura...

Please sign up or login with your details

Forgot password? Click here to reset