About

Aounon Kumar is a highly accomplished PhD candidate in Computer Science at the University of Maryland. His research focuses on designing machine learning algorithms that are robust against input corruptions, with a particular emphasis on deep neural networks. He has a strong background in a wide range of learning problems, including structured outputs such as semantic segmentation, image reconstruction, and object detection, as well as reinforcement learning and streaming tasks. Aounon's work has been instrumental in advancing the field of provable robustness, and he has designed guarantees for Wasserstein distribution shifts and explored the limitations of randomized smoothing-based robustness strategies for high-dimensional problems. His ultimate goal is to extend the scope of provable robustness to real-world machine learning tasks with complex outputs that cannot be easily modeled as a static single-shot prediction problem. In addition to his academic pursuits, Aounon has also gained valuable industry experience as an Applied Scientist Intern at Amazon. Prior to this, he served as a Graduate Research Assistant and Graduate Teaching Assistant at the University of Maryland. Aounon's educational background is equally impressive, with a PhD in Computer Science from the University of Maryland, a Master of Science in Computer Science from the Indian Institute of Technology, Delhi, and a Bachelor of Technology in Computer Science from IIT. He is a skilled researcher with expertise in areas such as research scientist, ML, reinforcement learning, object detection, and neural networks. Overall, Aounon Kumar is a highly talented and accomplished individual who has made significant contributions to the field of machine learning. He is a driven and dedicated researcher who is committed to advancing the state of the art in provable robustness and other areas of computer science.