Faster Convex Optimization: Simulated Annealing with an Efficient Universal Barrier
This work provides an efficient randomized interior point method with a universal barrier for any convex set, addressing a bottleneck in optimization for researchers and practitioners.
The paper tackles the problem of convex optimization under the membership oracle model by establishing an equivalence between simulated annealing and interior point methods, resulting in an improved time complexity that reduces by the square root of the dimension in some cases.
This paper explores a surprising equivalence between two seemingly-distinct convex optimization methods. We show that simulated annealing, a well-studied random walk algorithms, is directly equivalent, in a certain sense, to the central path interior point algorithm for the the entropic universal barrier function. This connection exhibits several benefits. First, we are able improve the state of the art time complexity for convex optimization under the membership oracle model. We improve the analysis of the randomized algorithm of Kalai and Vempala by utilizing tools developed by Nesterov and Nemirovskii that underly the central path following interior point algorithm. We are able to tighten the temperature schedule for simulated annealing which gives an improved running time, reducing by square root of the dimension in certain instances. Second, we get an efficient randomized interior point method with an efficiently computable universal barrier for any convex set described by a membership oracle. Previously, efficiently computable barriers were known only for particular convex sets.