Rick Johnson, an engineering professor on the Hill—and, at the risk of a mixed metaphor, something of a Renaissance man. At Cornell since 1981, Johnson has spent decades teaching and doing research in electrical engineering, particularly in the fields of control systems and signal processing. But over the past twelve years, his interests have entailed as much art as science. A pioneer in the field of computational art history, Johnson leverages both his engineering acumen and his abiding passion for art to study the physical materials with which works are made. Read more about Magic Eye
Today’s Data Science: Expectations and Constraints
Human expectations from modern data science and machine learning systems are growing. We demand results: as fast as possible; using as little data as possible; in as little space as possible; with as little communication with other entities as possible; leaking as little personal information as possible; and importantly, as accurately as possible. These constraints, however, are often at odds with each other. A system that provides strong privacy guarantees might require more data and computation, and a system that uses little data might require more computation. In spite of many success stories of data science, these trade-offs are poorly understood even in some of the simplest settings.
Jayadev Acharya, Electrical and Computer Engineering, is formulating and studying fundamental trade-offs between these resources, as well as design efficient schemes that achieve them. This is critical for tackling the many challenges in data science that lay ahead.
The project’s outcomes will help design faster, communication-frugal, privacy-preserving, and space-efficient learning systems.
A particular interest is the impact of the availability of shared randomness on the other constraints for distributed machine learning systems. While the role of randomness has been studied in communication complexity problems, its role in machine learning systems is often overlooked. Acharya is integrating ideas from computer science, information theory, machine learning, and statistics in order to bridge researchers from these communities. He is also working with a diverse group of researchers through outreach activities that target undergraduate students and underrepresented communities.
Original article by Cornell Research
Image credit (graphic): Beatrice Jin
Other Articles of Interest
The Kent Active Management System (KASM) project with United Kingdom Power Networks (UKPN) has won the 2019 “Innovation Project of the Year” at the Networks Awards in Birmingham, UK. As technical lead... Read more about Project wins industry innovation award