An efficient gradient-free line search

This paper introduces a new line search along an arbitrary smooth search path that starts at the current iterate tangentially to a descent direction. Like the Goldstein line search and unlike the Wolfe line search, the new line search uses, beyond the gradient at the current iterate, only function values. Using this line search with search directions satisfying the bounded angle condition, global convergence to a stationary point is proved for continuously differentiable objective functions that are bounded below and have Lipschitz continuous gradients. Complexity bounds are proved under several natural assumptions.



View An efficient gradient-free line search