A weak tail-bound probabilistic condition for function estimation in stochastic derivative-free optimization

In this paper, we use tail bounds to define a tailored probabilistic condition for function estimation that eases the theoretical analysis of stochastic derivative-free optimization methods. In particular, we focus on the unconstrained minimization of a potentially non-smooth function, whose values can only be estimated via stochastic observations, and give a simplified convergence proof for both a direct search and a basic trust-region scheme.

Citation

F. Rinaldi, L. N. Vicente, and D. Zeffiro, A weak tail-bound probabilistic condition for function estimation in stochastic derivative-free optimization, ISE Technical Report 22T-002, Lehigh University.

Article

Download

View A weak tail-bound probabilistic condition for function estimation in stochastic derivative-free optimization