Optimization
Robust Matrix Sensing in the Semi-Random Model
Low-rank matrix recovery is a fundamental problem in machine learning with numerous applications.
Distributionally Robust Skeleton Learning of Discrete Bayesian Networks Y eshu Li
The DAG structure of a Bayesian network is typically unknown in practice [Natori et al., 2017,
Convergence Analysis of ODE Models for Accelerated First-Order Methods via Positive Semidefinite Kernels
Consequently, our framework transforms the task of proving convergence rate into verifying the positive semidefiniteness of a specific integral kernel.
c056d6cf7b7108418f2b8c307dfaab02-Paper-Conference.pdf
Further, we are interested in algorithms that enjoy sample efficiency while leveraging (value) function approximation.
