ASOC: An Adaptive Parameter-free Stochastic Optimization Techinique for Continuous Variables
This addresses the need for more flexible and easier-to-use optimization algorithms in fields like machine learning and engineering, though it appears incremental as it builds on existing stochastic methods.
The paper tackles the problem of stochastic optimization for non-convex problems, where existing methods require user-defined parameters and lack adaptability to changing search spaces, by proposing ASOC, an adaptive parameter-free technique for continuous variables.
Stochastic optimization is an important task in many optimization problems where the tasks are not expressible as convex optimization problems. In the case of non-convex optimization problems, various different stochastic algorithms like simulated annealing, evolutionary algorithms, and tabu search are available. Most of these algorithms require user-defined parameters specific to the problem in order to find out the optimal solution. Moreover, in many situations, iterative fine-tunings are required for the user-defined parameters, and therefore these algorithms cannot adapt if the search space and the optima changes over time. In this paper we propose an \underline{a}daptive parameter-free \underline{s}tochastic \underline{o}ptimization technique for \underline{c}ontinuous random variables called ASOC.