2021/06/11 by Billy Jin, Jin, Billy, Katya Scheinberg +3 · 3 citations
Computer Science · Decision Sciences · Engineering · #Advanced Bandit Algorithms Research #FOS: Mathematics #Optimization and Control (math.OC) #Sparse and Compressive Sensing Techniques #Stochastic Gradient Optimization Techniques
paper · pdf · doi:10.48550/arxiv.2106.06454
openalex publication_date 2021/06/11 · openalex created_date 2022/07/28 · openalex updated_date 2026/07/28
We consider a step search method for continuous optimization under a stochastic setting where the function values and gradients are available only through inexact probabilistic zeroth- and first-order oracles. Unlike the stochastic gradient method and its many variants, the algorithm does not use a pre-specified sequence of step sizes but increases or decreases the step size adaptively according to the estimated progress of the algorithm. These oracles capture multiple standard settings including expected loss minimization and zeroth-order optimization. Moreover, our framework is very general and allows the function and gradient estimates to be biased. The proposed algorithm is simple to describe and easy to implement. Under fairly general conditions on the oracles, we derive a high probability tail bound on the iteration complexity of the algorithm when it is applied to non-convex, convex, and strongly convex (more generally, those satisfying the PL condition) functions. Our analysis strengthens and extends prior results for stochastic step and line search methods.