Complexity Analysis Framework of Adaptive Optimization Methods via Martingales

Abstract: We will present a very general framework for unconstrained adaptive optimization which encompasses standard methods such as line search and trust region methods that use stochastic function measurements and/or derivatives. In particular, methods that fall in this framework retain desirable practical features such as step acceptance criterion, trust region adjustment and ability to utilize second order models and enjoy the same convergence rates as their deterministic counterparts. The framework is based on bounding the expected stopping time of a stochastic process, which satisfies certain assumptions. Thus this framework provides strong convergence analysis under weaker conditions than alternative approaches in the literature. We will conclude with a discussion about some interesting open questions.

optimization and control

Audience: advanced learners

Comments: The address and password of the zoom room of the seminar are sent by e-mail on the mailinglist of the seminar one day before each talk

---

One World Optimization seminar

Series comments: Description: Online seminar on optimization and related areas

The address and password of the zoom room of the seminar are sent by e-mail on the mailinglist of the seminar one day before each talk

---