Skip to yearly menu bar Skip to main content


Entrywise convergence of iterative methods for eigenproblems

Vasileios Charisopoulos · Austin Benson · Anil Damle

Poster Session 4 #1245

Keywords: [ Reinforcement Learning ] [ Reinforcement Learning and Planning ] [ Learning Theory ] [ Reinforcement Learning and Planning -> Exploration; Theory ]


Several problems in machine learning, statistics, and other fields rely on computing eigenvectors. For large scale problems, the computation of these eigenvectors is typically performed via iterative schemes such as subspace iteration or Krylov methods. While there is classical and comprehensive analysis for subspace convergence guarantees with respect to the spectral norm, in many modern applications other notions of subspace distance are more appropriate. Recent theoretical work has focused on perturbations of subspaces measured in the ℓ2→∞ norm, but does not consider the actual computation of eigenvectors. Here we address the convergence of subspace iteration when distances are measured in the ℓ2→∞ norm and provide deterministic bounds. We complement our analysis with a practical stopping criterion and demonstrate its applicability via numerical experiments. Our results show that one can get comparable performance on downstream tasks while requiring fewer iterations, thereby saving substantial computational time.

Chat is not available.