Uploaded August 2020 | Updated September 2026, 2 weeks ago
For a number of years, the IMA has been running a series of conferences to promote mathematics with the aim of demonstrating to both mathematicians and non-mathematicians the many uses of modern mathematics.
This summer, due to Covid19, IMA Mathematics 2020 was transformed into a series of online events. Ned Allen & Kristen Pudenz from Lockheed Martin presented the first talk for Week Two of the IMA Mathematics 2020 Online Series. Their talk was on Open Mathematical Questions to Illuminate Quantum Machine Learning (QML)
Abstract
“Machine learning derives powerful results fueled by vast computational resources, which consistently lead mathematical efforts to explain and guide the models being used. Discoveries fueled by machine learning span biology, sociology, economics, and the hard sciences. With the advent of quantum computing as a practical engineering discipline, the space of available machine learning structures underlying data and algorithms is further expanded. One of the leading candidates for near term applications of quantum computing, quantum machine learning could benefit tremendously from theoretical advances contributed by the mathematics community.
We will cover the differences between resources available to classical and quantum computers, selected models that have been proposed for quantum machine learning, and industrial applications motivating progress in the field. Relevant open mathematical questions in the field will be highlighted, including the representation capabilities of quantum neural networks, appropriate restrictions on neural network structure to improve trainability and generalization without compromising learning potential, and the types of problems likely to be more brightly illuminated by quantum machine learning than by classical treatments."
The IMA Mathematics 2020 Online Series has been organised in collaboration with the Newton Gateway to Mathematics.
For a number of years, the IMA has been running a series of conferences to promote mathematics with the aim of demonstrating to both mathematicians and non-mathematicians the many uses of modern mathematics.
This summer, due to Covid19, IMA Mathematics 2020 was transformed into a series of online events. Ned Allen & Kristen Pudenz from Lockheed Martin presented the first talk for Week Two of the IMA Mathematics 2020 Online Series. Their talk was on Open Mathematical Questions to Illuminate Quantum Machine Learning (QML)
Abstract
“Machine learning derives powerful results fueled by vast computational resources, which consistently lead mathematical efforts to explain and guide the models being used. Discoveries fueled by machine learning span biology, sociology, economics, and the hard sciences. With the advent of quantum computing as a practical engineering discipline, the space of available machine learning structures underlying data and algorithms is further expanded. One of the leading candidates for near term applications of quantum computing, quantum machine learning could benefit tremendously from theoretical advances contributed by the mathematics community.
We will cover the differences between resources available to classical and quantum computers, selected models that have been proposed for quantum machine learning, and industrial applications motivating progress in the field. Relevant open mathematical questions in the field will be highlighted, including the representation capabilities of quantum neural networks, appropriate restrictions on neural network structure to improve trainability and generalization without compromising learning potential, and the types of problems likely to be more brightly illuminated by quantum machine learning than by classical treatments."
The IMA Mathematics 2020 Online Series has been organised in collaboration with the Newton Gateway to Mathematics.
