Mathematics Colloquia and Seminars

Return to Colloquia & Seminar listing

Towards Scalable Algorithms for Distributed Optimization and Learning

Special Events

Speaker: Cesar Uribe, MIT
Location: 1147 MSB
Start time: Mon, Jan 13 2020, 4:10PM

Increasing amounts of data generated by modern complex systems such as the energy grid, social media platforms, sensor networks, and cloud-based services call for attention to distributed data processing, in particular, for the design of scalable algorithms that take into account storage and communication constraints and help to make coordinated decisions. In this talk, we present recently proposed distributed algorithms with optimal convergence rates for optimization problems over networks, where data is stored distributedly. We focus on scalable algorithms and show they can achieve the same rates as their centralized counterparts, with an additional cost related to the structure of the network. We provide application examples to distributed inference and learning, and computational optimal transport.



Meet the speaker at a reception starting 3:45pm in 1147 MSB. Refreshments will be served.