High-Dimensional Robust Statistics with Ilias Diakonikolas

Ilias Diakonikolas is faculty in the Computer Science Department at the University of Wisconsin-Madison where his main research interests are in algorithms and machine learning. His work focuses on understanding the tradeoff between statistical efficiency, computational efficiency, and robustness for fundamental problems in statistics and machine learning, where robustness refers broadly to a model’s ability to deal with noisy data.

Ilias recently won the Outstanding Paper award at NeurIPS for his work, Distribution-Independent PAC Learning of Halfspaces with Massart Noise, which focuses on an area called high-dimensional robust learning and is essentially the first progress made around distribution-independent learning with noise since the 80s.

*Nerd Alert!!* If you enjoy our more technical conversations, heads up that this interview won’t disappoint.