|
Speaker: Quanquan C. Liu Assistant Professor of Computer Science at Yale University Wednesday, September 4, 2024 Lunch in 1307 at 11:30am; Talk at 12:00pm in 1327; Zoom: https://yale.zoom.us/j/7859884026?omn=91367400113 Location: Yale Institute for Foundations of Data Science & Webcast, 219 Prospect Street, New Haven, CT 06511 |
Add To: Google Calendar | Outlook | iCal File
“Massive Graph Algorithms from Theory to Practice and Back”
Abstract: In the face of massive graph data, there is increased interest in developing novel algorithmic foundations for practical graph algorithms that are scalable, efficient, and private. Algorithm designers face many challenges when creating algorithms for real-world deployment. First, modern datasets often reach sizes of hundreds of gigabytes or even terabytes of data. Second, data is constantly evolving, and we require accurate temporal statistics despite these changes. Finally, the widespread use of sensitive user data poses a great threat to user privacy. Theoretical models have been developed to model each of these situations including the shared-memory parallel, massively parallel computation, dynamic/batch-dynamic, and differential privacy models. This talk will introduce these models, give example algorithms in these models, and discuss challenges and potential solutions in translating these algorithms from theory to practice and back.
Speaker Bio: Quanquan C. Liu is an assistant professor in the Computer Science department at Yale and is a member of the Yale Institute for Foundations of Data Science. Her current interests feature the theory and practice of algorithms for large data, graph algorithms, and various notions of stability, especially in the connections between these notions.
