Published on Wed May 29 2019

Accelerating Min-Max Optimization with Application to Minimal Bounding Sphere

Hakan Gokcesu, Kaan Gokcesu, Suleyman Serdar Kozat

We study the min-max optimization problem where each function contributing to the max operation is strongly-convex and smooth with bounded gradient. By smoothing the max operator, we show the ability to achieve an arbitrarily small positive optimality gap of $O(1/\delta)

0
0
0
Abstract

We study the min-max optimization problem where each function contributing to the max operation is strongly-convex and smooth with bounded gradient in the search domain. By smoothing the max operator, we show the ability to achieve an arbitrarily small positive optimality gap of $\delta$ in $\tilde{O}(1/\sqrt{\delta})$ computational complexity (up to logarithmic factors) as opposed to the state-of-the-art strong-convexity computational requirement of $O(1/\delta)$. We apply this important result to the well-known minimal bounding sphere problem and demonstrate that we can achieve a $(1+\varepsilon)$-approximation of the minimal bounding sphere, i.e. identify an hypersphere enclosing a total of $n$ given points in the $d$ dimensional unbounded space $\mathbb{R}^d$ with a radius at most $(1+\varepsilon)$ times the actual minimal bounding sphere radius for an arbitrarily small positive $\varepsilon$, in $\tilde{O}(n d /\sqrt{\varepsilon})$ computational time as opposed to the state-of-the-art approach of core-set methodology, which needs $O(n d /\varepsilon)$ computational time.