The Institute of Mathematical Statistics (IMS) has announced its 2024 class of IMS Fellows, and Venu Veeravalli is among them.
According to the award citation, he received the honor “for outstanding contributions to sequential hypothesis testing and quickest change detection.”
The IMS is an international society founded in 1935 to promote “the development, dissemination, and application of statistics and probability.” It has awarded Fellow designations for over 85 years; according to its website, the honor goes to individuals who have “demonstrated distinction in research or leadership that has profoundly influenced the field.”
Today, Veeravalli is the Henry Magnuski Professor in Electrical & Computer Engineering and is also affiliated with the Department of Statistics, the Coordinated Science Laboratory and the Discovery Partners Institute. But the story of how he came to win the IMS Fellow honor started more than 30 years ago.
Veeravalli was pursuing his doctorate at UIUC under the guidance of H. Vincent Poor and Tamer Başar when he took a Statistics course in sequential analysis taught by Adam T. Martinsek. Veeravalli recently described Martinsek, who is now an Emeritus Professor in Statistics and an IMS Fellow himself, as one of his “most inspiring professors.”
In that class, Veeravalli collaborated with another student, Carl Baum, on a project on sequential multihypothesis testing. They ended up submitting a writeup of the project to the IEEE Transactions on Information Theory. The paper attracted considerable attention and eventually won the 1996 IEEE Browder J. Thompson Memorial Prize Award (an award presented for “the most outstanding paper in any IEEE publication... by... authors under thirty years of age”).
As Veeravalli recently recalled, the experience of working on this paper “motivated me to further explore related topics in sequential analysis.” An area in which he has made a number of contributions is quickest change detection (QCD), in which one tries to identify a significant change in the distribution of a data sequence as quickly as possible after the change occurs, while keeping the false alarm rate at a desired level.
Veeravalli explained that QCD has many engineering applications. For example, in collaboration with Alejandro Domínguez-García, he has developed and applied QCD algorithms to detect line outages in power systems. Under recent NSF funding, he successfully applied his work to a pandemic monitoring solution; he developed algorithms that can quickly predict the next wave of a pandemic (such as COVID-19) based on noisy test data, such as from wastewater monitoring. He’s also using QCD algorithms for anomaly detection in a large UIUC-led Internet of Battlefield Things (IoBT) project supported by the Army Research Laboratory.
But Veeravalli said that such engineering applications alone wouldn’t have attracted the IMS Fellow honor. Rather, the IMS would have been interested in his theoretical contributions, such as the performance bounds and asymptotic analyses he had to develop to enable those engineering applications.
Veeravalli isn’t the first engineer to receive an IMS Fellowship; indeed, his Ph.D. co-advisor, Vince Poor, is a recipient of this honor as well. But IMS Fellowships aren’t often bestowed on engineers, making Veeravalli’s designation particularly special.
“I feel humbled to be part of a fellowship that includes many of my academic heroes who have made profound contributions to mathematical statistics and probability theory,” he said.