I am broadly interested in the mathematical foundations of data science, with primary focuses on theory and algorithms for large-scale optimization problems from engineering and data science and machine learning for graphical data. My research interests broadly include:

• Convex and nonconvex optimization
• Distributed (and decentralized) optimization
• Artificial intelligence and scientific machine learning (especially on graphical data)
• Mathematical foundations of data science

My research focuses on what I think of as “practical theory”, for example, designing algorithms that are both theoretically principled and effective for real-world problems. I'm especially drawn to ideas that are simple, intuitive, and — at least to me — elegant. Being a theoretician isn't about collecting theorems, just like being a writer isn't about stacking sentences. I work to understand core problems more deeply and explore when and why algorithms succeed or fail. As I continue to develop my research program, I'm excited to stay curious, learn from others, and contribute to the field with rigor and creativity.