Dhinakaran Vinayagamurthy, PhD candidate
David R. Cheriton School of Computer Science
Di Wang, Postdoctoral fellow
Georgia Institute of Technology
Li Liu, PhD candidate
David R. Cheriton School of Computer Science
Following my previous seminar talk on embezzlement of entanglement, this talk introduces a more general version of the problem — self-embezzlement. Instead of embezzling a pair of entangled state from a catalyst, self-embezzlement aims to create two copies of the catalyst state using only local operators.
Panos K. Chrysanthis
Department of Computer Science, University of Pittsburgh
Zeynep Korkmaz, PhD seminar
David R. Cheriton School of Computer Science
Analysis on graphs have powerful impact on solving many social and scientific problems, and applications often perform expensive traversals on large scale graphs. Caching approaches on top of persistent storage are among the classical solutions to handle high request throughput. However, graph processing applications have poor access locality, and caching algorithms do not improve disk I/O sufficiently.
Haotian Zhang, PhD candidate
David R. Cheriton School of Computer Science
Andreas Stöckel, PhD candidate
David R. Cheriton School of Computer Science
The artificial neurons typically employed in machine learning and computational neuroscience bear little resemblance to biological neurons. They are often derived from the “leaky integrate and fire” (LIF) model, neglect spatial extent, and assume a linear combination of input variables. It is well known that these simplifications have a profound impact on the family of functions that can be computed in a single-layer neural network.
Nabiha Asghar, PhD candidate
David R. Cheriton School of Computer Science
Joseph Haraldson, PhD candidate
David R. Cheriton School of Computer Science
We consider the problem of computing the nearest matrix polynomial with a non-trivial Smith Normal Form (SNF). This is a non-convex optimization problem where we find a nearby matrix polynomial with prescribed eigenvalues and associated multiplicity structure in the invariant factors.
Verena Kantere
School of Electrical Engineering and Computer Science, University of Ottawa
Big Data analytics in science and industry are performed on a range of heterogeneous data stores, both traditional and modern, and on a diversity of query engines. Workflows are difficult to design and implement since they span a variety of systems. To reduce development time and processing costs, some automation is needed.