FedEL: Federated Elastic Learning for Heterogeneous Devices
About Me
I am a first-year M.Phil. student at the University of Hong Kong, where I am fortunate to be advised by Prof. Yingyu Liang and Prof. Andrew F. Luo. My research interests are in the theoretical foundations of machine learning, I am also a Research Engineer Intern at Moonshot AI working on infrastructure.
Selected Publications
* denotes equal contribution or alphabetical order.
Circuit Complexity Bounds for RoPE-based Transformer Architecture*
Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent*