Quantum Machine Learning and the Power Method


Details
Hello all, I would like to welcome you all to the 22nd Meetup of KW Intersections on June 14th at 7pm at Boltmade (https://www.boltmade.com/). Michal Kononenko will teach us more about Quantum Machine Learning in his talk titled "Quantum Machine Learning: Or How I learned to Stop Worrying and Love the Hamiltonian". In the second part of the Meetup we will talk about the Power method or Power Iteration. As always our accommodation will be nicely provided by Boltmade (https://www.boltmade.com/) and for the first time Sortable (http://sortable.com/careers-at-sortable/) will feed us with some delicious pizza.
Quantum Machine Learning: Or How I Learned to Stop Worrying and Love the Hamiltonian by Michal Kononenko
This talk will reimplement the k-means clustering algorithm on a quantum computer, based off work done by Lloyd. As a result, the time complexity of the algorithm decreases from $O(n^2)$ to $O(n log n)$. Along the way, the talk will provide a practical introduction to quantum computing, explaining how the gate model of quantum computing emerges from physical principles, and how those principles serve to differentiate quantum algorithms from classical computation. The talk will conclude with a discussion of open problems in the field of quantum machine learning. Most of the information presented in this talk comes from Schuld et al. (http://arxiv.org/abs/1409.3097), as well as the user guide for IBM's Quantum Experience (https://quantumexperience.ng.bluemix.net/), their recently-released quantum cloud computing platform. A more detailed review of quantum machine learning is available in Lloyd et. al. (http://arxiv.org/abs/1307.0411)
Power Iteration or Power Method by Mary Loubele
TBA

Quantum Machine Learning and the Power Method