Xiang Cheng

I am an Assistant Professor at the Department of Electrical and Computer Engineering at Duke University.

I obtained my PhD at UC Berkeley, advised by Peter Bartlett and Michael Jordan, and was a postdoc at MIT with Suvrit Sra.

My research focuses on the design and analysis of geometric algorithms in AI and ML. I am specifically interested in the geometries present in deep neural networks, and the design of algorithms to exploit these geometries. I am also interested in geometric diffusion processes, for sampling and generative models.

[Google Scholar] [CV] [email]