Summary
Enmao Diao is a PhD student and applied scientist with 11 years of experience at the intersection of machine learning, federated learning, and model/data compression. He has driven research and practical systems at Duke, Amazon (Alexa), and Harvard, proposing frameworks such as HeteroFL, SemiFL, Gradient Assisted Learning, and scalable compression models like DRASIC and RRNN. His work spans theory—computing degrees of freedom for nonlinear models—to applied PyTorch pipelines for edge and decentralized settings, with a focus on heterogeneity, personalization, and privacy-aware collaboration. Based in Chengdu, he blends rigorous academic training from Georgia Tech, Harvard, and Duke with industry impact, and is noted for translating theoretical insights into scalable algorithms for resource-constrained devices.
12 years of coding experience
9 years of employment as a software developer
Doctor of Philosophy - PhD Electrical and Electronics Engineering, Doctor of Philosophy - PhD Electrical and Electronics Engineering at Duke University
Bachelor of Science (BS) Computer Science, Bachelor of Science (BS) Computer Science at Georgia Institute of Technology
Master of Science - MS Electrical and Electronics Engineering, Master of Science - MS Electrical and Electronics Engineering at Harvard University
English, Chinese