Ilias Diakonikolas Wins 2017 Sloan Research Fellowship

| March 10, 2017

Theoretical computer scientist Ilias Diakonikolas has received a prestigious two-year grant award from the Alfred P. Sloan Foundation

Ilias Diakonikolas, Winner of 2017 Sloan Research Fellowship. Photo/Noe Montes

Ilias Diakonikolas, an assistant professor and Andrew and Erna Viterbi Early Career Chair in USC Viterbi’s Department of Computer Science, has won a highly competitive Sloan Research Fellowship.

The award is a two-year, $60,000 fellowship granted by the Alfred P. Sloan Foundation, which recognizes promising early-career scientists who are making substantial contributions to their respective fields. Diakonikolas was one of just 16 Sloan Fellows named this year in computer science.

“This speaks to the fact that right now, machine learning and artificial intelligence are very hot topics in computer science,” said Gaurav Sukhatme, chair of the USC Viterbi Department of Computer Science. “Ilias is a very deep thinker and I’m thrilled that the Sloan Foundation is recognizing the fundamental contributions he is making to the field.”

Diakonikolas, who works on designing algorithms for machine learning, is what Sukhatme calls an algorithmic statistician. In a deep mathematical way, Diakonikolas seeks to understand the tradeoffs between efficiency and robustness in machine learning environments, with the ultimate goal of creating systems that are both highly efficient and highly robust.

“Ilias is one of very few people in the world who is really after a deep understanding of the tradeoffs in machine learning,” Sukhatme said.

In high-dimensional learning environments, when hundreds or thousands of variables are in use, outliers often exist which traditional mathematical models are unable to represent. Diakonikolas’ theoretical work helps computer scientists understand when algorithms can be relied upon, and when they will fail to accurately represent and respond to inputs.

Rather than working on a specific collection of data, Diakonikolas takes a broader view. “My goal is to develop general methods that work for broad families of data sets, so they can be applied in many different practical settings,” he said.

Indeed, the applications for his research are extremely diverse, spanning areas such as voice recognition or driverless cars.

A native of Greece, Diakonikolas earned his Ph.D. in computer science from Columbia University. He then completed two years of post-doctorate work at UC Berkeley, where he was a Simons Postdoctoral Fellow in theoretical computer science. He later served on the faculty at the University of Edinburgh.

Diakonikolas joined the USC faculty in 2016. This year, he has also received the NSF CAREER and Google Faculty Research Awards. He feels especially honored to accept the Sloan Research Fellowship.

“I am very happy for this recognition. This award is a strong motivation for me to continue performing fundamental algorithms research in machine learning,” he said.