Albert Gu is a PhD student in the Stanford CS department, and later [[Carnegie Mellon University]], currently being advised by [[Chris Ré]]. He is involved in research related to algorithms for structured linear algebra and theoretical principles of deep sequence models. Albert's work focuses on developing efficient algorithms for solving problems involving structured linear algebra. This involves studying and designing algorithms that exploit the underlying structure of matrices and vectors to perform computations more efficiently. By developing such algorithms, he aims to improve the performance and scalability of various applications that heavily rely on linear algebraic operations. In addition to his work on structured linear algebra, Albert is also interested in the theoretical principles underlying deep sequence models. Deep sequence models are a type of machine learning model that can process sequential data (such as text or time-series data) using multiple layers of artificial neural networks. Albert's research involves studying the theoretical aspects of these models, understanding their limitations, and proposing new techniques to overcome challenges associated with training and interpreting deep sequence models. Overall, Albert Gu's research interests lie at the intersection of algorithm design, linear algebra, and deep learning. He strives to develop innovative solutions to computational problems in these areas, with a focus on improving efficiency and advancing our theoretical understanding. # References ```dataview Table title as Title, authors as Authors where contains(authors, "Albert Gu") ```