This week, we continue our introduction to faculty research topics. We encourage all faculty members and MS/PhD students to attend and hope these presentations would help students meet faculty members and get exposed to the full range of the research portfolio in our department. We feature the following speakers this week:
Many social and scientific domains give rise to data with multi-way relationships that can naturally be represented by tensors, or multi-dimensional arrays. Decomposing – or factoring – tensors can reveal latent properties that are otherwise difficult to see. However, due to the relatively recent rise in popularity of tensor algorithms in HPC, its challenges in performance optimization is poorly understood. In this talk, we will discuss the similarities and differences between tensor algorithms and traditional linear algebra problems in the context of HPC, and how our prior experience in linear algebra on HPC systems can help us better formulate and solve these new problems, particularly in the context work and data distribution on parallel systems.