Adhyyan Narang

I am a fifth year PhD Student in the ECE Department of University of Washington, advised by Prof. Maryam Fazel and Prof. Lillian Ratliff.

My research focuses on developing theory for multi-agent and resource-constrained machine learning systems. Traditional learning theory studies ML from the perspective of a single agent in an isolated world, and assumes that training and test data comes from a fixed distribution. But in the real world, data is generated by humans, which is consumed by multiple agents, who then deploy models that affect the distribution of data. How do we ensure positive outcomes for all agents in such settings?

Broadly, I am interested in working towards the goal of Holistic Artificial Intelligence: AIs that can integrate smoothly and harmoniously into the natural and economic systems that they are a part of, and provide sustained value over the long-term. The traditional framing of value-alignment between AIs and humans is necessary but not sufficient to achieve this goal.

Prior to joining UW, I completed my Masters in 2020 in the BLISS Lab in the EECS department at UC Berkeley, where I was advised by Prof. Anant Sahai. I completed my undergraduate studies at UC Berkeley with a major in EECS and minor in Theater.