A Random Walk Approach to First-Order Stochastic Convex Optimization

back to our research

A Random Walk Approach to First-Order Stochastic Convex Optimization

July 7 - 12 2019 ISIT, Paris, France

Authors: Sattar Vakili and Qing Zhao (Cornell University)

Abstract: An active search strategy based on devising a biased random walk on an infinite-depth tree constructed through successive partitioning of the search domain is developed. By localizing data processing to small subsets of the input domain based on the tree structure, it enjoys very low computation and memory complexity and allows dynamic allocation of limited data storage.

Multi-agent Systems


See paper

Join us to make AI that will change the world

join our team