Physicists uncover similarities between classical and quantum machine learning

May 31, 2017 by Lisa Zyga, Phys.org feature
Diagram representing a generic quantum learning protocol. Credit: Monràs et al. ©2017 American Physical Society

(Phys.org)—Physicists have found that the structure of certain types of quantum learning algorithms is very similar to their classical counterparts—a finding that will help scientists further develop the quantum versions. Classical machine learning algorithms are currently used for performing complex computational tasks, such as pattern recognition or classification in large amounts of data, and constitute a crucial part of many modern technologies. The aim of quantum learning algorithms is to bring these features into scenarios where information is in a fully quantum form.

The scientists, Alex Monràs at the Autonomous University of Barcelona, Spain; Gael Sentís at the University of the Basque Country, Spain, and the University of Siegen, Germany; and Peter Wittek at ICFO-The Institute of Photonic Science, Spain, and the University of Borås, Sweden, have published a paper on their results in a recent issue of Physical Review Letters.

"Our work unveils the structure of a general class of learning algorithms at a very fundamental level," Sentís told Phys.org. "It shows that the potentially very complex operations involved in an optimal quantum setup can be dropped in favor of a much simpler operational scheme, which is analogous to the one used in classical algorithms, and no performance is lost in the process. This finding helps in establishing the ultimate capabilities of quantum learning algorithms, and opens the door to applying key results in to quantum scenarios."

In their study, the physicists focused on a specific type of machine learning called inductive supervised learning. Here, the is given training instances from which it extracts general rules, and then applies these rules to a variety of test (or problem) instances, which are the actual problems that the algorithm is trained for. The scientists showed that both classical and quantum inductive supervised learning algorithms must have these two phases (a training phase and a test phase) that are completely distinct and independent. While in the classical setup this result follows trivially from the nature of classical information, the physicists showed that in the quantum case it is a consequence of the quantum no-cloning theorem—a theorem that prohibits making a perfect copy of a quantum state.

By revealing this similarity, the new results generalize some key ideas in classical statistical learning theory to quantum scenarios. Essentially, this generalization reduces complex protocols to simpler ones without losing performance, making it easier to develop and implement them. For instance, one potential benefit is the ability to access the state of the learning algorithm in between the training and test phases. Building on these results, the researchers expect that future work could lead to a fully quantum theory of risk bounds in quantum statistical learning.

"Inductive supervised quantum learning algorithms will be used to classify information stored in quantum systems in an automated and adaptable way, once trained with sample systems," Sentís said. "They will be potentially useful in all sorts of situations where information is naturally found in a quantum form, and will likely be a part of future quantum information processing protocols. Our results will help in designing and benchmarking these algorithms against the best achievable performance allowed by quantum mechanics."

Explore further: Physicists extend quantum machine learning to infinite dimensions

More information: Alex Monràs et al. "Inductive Supervised Quantum Learning." Physical Review Letters 118, 190503. DOI: 10.1103/PhysRevLett.118.190503

Related Stories

Mapping the edge of reality

April 28, 2017

Australian and German researchers have collaborated to develop a genetic algorithm to confirm the rejection of classical notions of causality.

How quantum effects could improve artificial intelligence

October 17, 2016

(Phys.org)—Over the past few decades, quantum effects have greatly improved many areas of information science, including computing, cryptography, and secure communication. More recently, research has suggested that quantum ...

Artificial intelligence in quantum systems, too

February 22, 2017

Quantum biomimetics consists of reproducing in quantum systems certain properties exclusive to living organisms. Researchers at University of the Basque Country have imitated natural selection, learning and memory in a new ...

Recommended for you

Integrating optical components into existing chip designs

April 19, 2018

Two and a half years ago, a team of researchers led by groups at MIT, the University of California at Berkeley, and Boston University announced a milestone: the fabrication of a working microprocessor, built using only existing ...

2 comments

Adjust slider to filter visible comments by rank

Display comments: newest first

swordsman
not rated yet Jun 01, 2017
If the classical method works better, then why consider quantum methodology, which is more limited?
Dingbone
Jun 01, 2017
This comment has been removed by a moderator.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.