USP paired with VAW delivers O(log^3 T) regret for marginally stable linear dynamical systems with asymmetric hidden matrices.
A new approach to learning linear dynamical systems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Derives instance-specific lower bounds on sample complexity for rank-adaptive matrix estimation and proposes a least-squares plus universal singular-value-thresholding algorithm whose finite-sample error nearly matches those bounds.
citing papers explorer
-
The Power of Second Order Methods for Sequence Preconditioning
USP paired with VAW delivers O(log^3 T) regret for marginally stable linear dynamical systems with asymmetric hidden matrices.
-
Near-optimal Rank Adaptive Inference of High Dimensional Matrices
Derives instance-specific lower bounds on sample complexity for rank-adaptive matrix estimation and proposes a least-squares plus universal singular-value-thresholding algorithm whose finite-sample error nearly matches those bounds.