CQT researchers and their collaborator present a quantum speed-up for machine learning
One of the ways that computers ‘think’ is by analysing relationships within large sets of data. CQT’s Jansen (Zhikuan) Zhao, Anupam Prakash and their collaborator have shown that quantum computers can do one such analysis faster than classical computers, for a wider array of data types than was previously expected.
The team’s proposed ‘quantum linear system algorithm’ is published in the 2 February issue of Physical Review Letters. In the future, it could help crunch numbers on problems as varied as commodities pricing, social networks and chemical structures.
“The previous quantum algorithm of this kind applied to a very specific type of problem. We need an upgrade if we want to achieve a quantum speed up for other data,” says Jansen, who is corresponding author on the work.
That’s exactly what the team is offering. The CQT researchers began collaborating with Leonard Wossnig when he visited the Centre. He was then a Master’s Student at ETH Zurich. Jansen is a PhD student, and Anupam is a research fellow. Jansen’s PhD is with the Singapore University of Technology and Design.
The first quantum linear system algorithm was proposed in 2009 by a different group of researchers. That algorithm kick-started research into quantum forms of machine learning, or artificial intelligence.
A linear system algorithm works on a large matrix of data. For example, a trader might be trying to predict the future price of goods. The matrix may capture historical data about price movements over time and data about features that could be influencing these prices, such as currency exchange rates. The algorithm calculates how strongly each feature is correlated with another by ‘inverting’ the matrix. This information can then be used to extrapolate into the future.
“There is a lot of computation involved in analysing the matrix. When it gets beyond say 10,000 by 10,000 entries, it becomes hard for classical computers,” explains Jansen. This is because the number of computational steps goes up rapidly with the number of elements in the matrix: every doubling of the matrix size increases the length of the calculation eight-fold.
The 2009 algorithm could cope better with bigger matrices, but only if the data in them is what’s known as ‘sparse’. In these cases, there are limited relationships among the elements, which is often not true of real-world data.
Jansen, Anupam and Leonard present a new algorithm that is faster than both the classical and the previous quantum versions, without restrictions on the kind of data it works for.
As a rough guide, for a 10,000 square matrix, the classical algorithm would take on the order of a trillion computational steps, the first quantum algorithm some 10,000s of steps and the new quantum algorithm just 100s of steps. The algorithm relies on a technique known as quantum singular value estimation.
There have been a few proof-of-principle demonstrations of the earlier quantum linear system algorithm on small-scale quantum computers. Jansen and his colleagues hope to work with an experimental group to run a proof-of-principle demonstration of their algorithm, too. They also want to do a full analysis of the effort required to implement the algorithm, checking what overhead costs there may be.
To show a real quantum advantage over the classical algorithms will need bigger quantum computers. Jansen estimates that “We’re maybe looking at three to five years in the future when we can actually use the hardware built by the experimentalists to do meaningful quantum computation with application in artificial intelligence.”
Learn more: Quantum algorithm could help AI think faster
The Latest on: Machine learning
- New Machine Learning system may help debunk fake news on October 6, 2018 at 9:16 pm
New York, Oct 6 : To combat fake news, a team of Massachusetts Institute of Technology (MIT) researchers have developed a new Machine Learning (ML) system that helps to determine whether a news source ... […]
- Deep Learning Is Great, But Use Cases Remain Narrow on October 5, 2018 at 11:41 am
However, despite the advantages that deep neural networks can bring for certain applications, the actual use cases for deep learning in the real world remain narrow, as traditional machine learning me... […]
- Symposium examines the potential of machine learning in health care on October 5, 2018 at 9:56 am
The excitement around machine learning in medicine has permeated the world of clinicians and researchers. While artificial intelligence is unlikely to replace medical professionals in the near future, ... […]
- Active Machine Learning Now Available in the VenioOne Platform on October 5, 2018 at 9:33 am
Super charge human reviewers with VenioOne's Continuous Active Learning and eliminate the tedious workflows of TAR 1.0. VenioOne CAL is now hitting its stride as a best of both worlds eDiscovery solut... […]
- Google to release DeepMind's StreetLearn for teaching machine-learning agents to navigate cities on October 5, 2018 at 7:57 am
Google is getting ready to release its StreetLearn dataset for training machine-learning models to navigate cities without a map. The StreetLearn environment relies on images from Google Street View a... […]
- What Role Can Machine Learning And AI Play In Banking And Lending? on October 5, 2018 at 6:00 am
Opinions expressed by Forbes Contributors are their own. You remember the old days of banking, right? We’re talking the mid-1950s: The days where you’d walk in, shake the hand of a man in professional ... […]
- AdSense Giving Machine Learning to Publishers on October 5, 2018 at 3:07 am
Google announced three changes coming to AdSense. The most exciting change is the introduction of machine learning technology for AdSense publishers. AdSense will give publishers access to machine lea... […]
- Curious Case of Actuarial Science, Geocoding, and Machine Learning on October 5, 2018 at 2:30 am
Did you know that 50- 80% of your enterprise business processes can be automated with AssistEdge? Identify processes, deploy bots and scale effortlessly with AssistEdge. This article illustrates ... […]
- MIT tackles fake news with machine learning system that classifies accuracy and bias on October 4, 2018 at 10:28 pm
A team of researchers from MIT's Computer Science and Artificial Intelligence Lab and the Qatar Computing Research Institute has set out to develop a new machine learning system designed to ... […]
- A powerful machine learning system used by Microsoft has been released to the world on October 4, 2018 at 10:17 pm
A machine learning system that’s so advanced it’s been used to gain a new understanding of childhood asthma has been made available for everyone to use. Microsoft’s Infer.NET has been released on the ... […]
via Google News and Bing News