Inexact restoration with subsampled trust-region methods for finite-sum minimization

Understand

Convex and nonconvex finite-sum minimization arises in many scientific computing and machine learning applications.

• Recently, first-order and second-order methods where objective functions, gradients and Hessians are approximated by randomly sampling components of the sum have received great attention.
• We propose a new trust-region method which employs suitable approximations of the objective function, gradient and Hessian built via random subsampling techniques.
• The choice of the sample size is deterministic and ruled by the inexact restoration approach.