1. Published a paper titled 'MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention', which presents a new approach that uses the Monarch matrix structure along with variational softmax to quickly and accurately approximate softmax attention in a zero-shot setting.
2. Published a paper titled 'Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective', providing theoretical results on the capabilities of attention for in-context learning.
3. The paper 'A Semidefinite Relaxation for Sums of Heterogeneous Quadratic Forms on the Stiefel Manifold' was published in the SIAM Journal on Matrix Analysis and Applications.
Research Experience
Leads the SPADA lab, focusing on research projects in statistical signal processing, matrix factorization, and optimization.
Education
No specific educational background information provided.
Background
Associate Professor of Electrical Engineering and Computer Science, Associate Chair for Undergraduate Affairs in the Division of Electrical and Computer Engineering, and an Associate Professor of Statistics by courtesy. IEEE University of Michigan Student Branch Counselor. Leads the Signal Processing Algorithm Design and Analysis (SPADA) lab. Her research focuses on statistical signal processing, matrix factorization, and optimization, particularly dealing with large and messy data. Her interests are theoretical, but her favorite mathematical problems are motivated by fascinating and important engineering problems.
Miscellany
No additional personal interests or hobbies provided.