BEGIN:VCALENDAR
BEGIN:VEVENT
SUMMARY:"Readying Machine Learning for Quantum Computing"
DESCRIPTION:Speaker: Hartmut Neven, Google
Talk Title: "Readying Machine Learning for Quantum Computing"
Abstract: Modern approaches to machine learning formulate training of a classifier as an optimization problem in which simultaneously the training error as well as the classifier complexity is minimized. For computational efficiency typically a convex objective is constructed. But it is well known that such a choice comes at a cost. For instance, convex loss functions designed to measure training performance are not as robust to noise as their non-convex counter parts and convex regularization does\n
not achieve as high levels of sparsity as versions involving the L0-norm. Non-convex losses also figure prominently in recent attempts to derive tighter bounds for the generalization error. Here we report on experiments to train with non-convex objectives using discrete optimization in a formulation adapted to take advantage of emerging hardware for quantum optimization. A key finding is that the resulting\n
classifiers are already competitive when using as temporary stand-in a classical heuristic solver. We will give an overview of the state of the quantum hardware development as well as what advantages in terms of quality of the solution we can hope to attain from a theoretical point of view.
Host: Daniel Lidar
DTSTART:20110527T140000
LOCATION:SSL 150
URL;VALUE=URI:
DTEND:20110527T150000
END:VEVENT
END:VCALENDAR