"Without transparency, AI cannot earn trust and wide adoption"
I am an Assistant Professor at the University of Virginia with appointments in the Data Science School, the Department of Computer Science, and School of Medicine. I lead the Aikyam Lab — "Aikyam" is Sanskrit for oneness.
Before joining UVA, I was a Research Scientist at Adobe Research and a Postdoctoral Fellow at Harvard University. I completed my Ph.D. in Electrical and Computer Engineering at the University of Illinois at Chicago. My research develops Trustworthy Machine Learning Frameworks — beyond training models for specific tasks — that satisfy explainability, fairness, and robustness. I believe breakthroughs happen when diverse people, ideas, and data come together.
He has authored in top-tier machine learning and computer vision conferences and leading scientific journals. His research has received Spotlight and Oral presentations at NeurIPS, ICML, AAAI, CVPR, and ICIP. Dr. Agarwal has received industrial grants from Adobe, Microsoft, and Google to support his work on Trustworthy Machine Learning. His algorithm are used to understand industry-scale models in Amazon for surfacing important data points and showing that deploying an industry scale model trained only on half the data as surfaced does not lead to performance degradations.
I am the founder of the Agyeya Artificial IQ Foundation, focused on democratizing AI research and training the next generation of AI students in India. Learn more at our outreach page.
