Block coordinate descent on smooth manifolds: Convergence theory and twenty-one examples
Block coordinate descent is an optimization paradigm that iteratively updates one block of
variables at a time, making it quite amenable to big data applications due to its scalability …
variables at a time, making it quite amenable to big data applications due to its scalability …
Asymptotic mutual information in quadratic estimation problems over compact groups
KY Yang, TLH Wee, Z Fan - arXiv preprint arXiv:2404.10169, 2024 - arxiv.org
Motivated by applications to group synchronization and quadratic assignment on random
data, we study a general problem of Bayesian inference of an unknown``signal''belonging to …
data, we study a general problem of Bayesian inference of an unknown``signal''belonging to …