Smoothed Analysis of Interior-Point Algorithms: Condition Number
We show that the smoothed complexity of the logarithm of Renegar's condition number is O(log (n/sigma)).
cs.DS↗
arXiv subjects
Shang-Hua Teng
Publications and source records attributed to Shang-Hua Teng.
Smoothed Analysis of Algorithms: Why the Simplex Algorithm Usually Takes Polynomial Time
We introduce the smoothed analysis of algorithms, which is a hybrid of the worst-case and average-case analysis of algorithms. In smoothed analysis, we measure the maximum over inputs of the expected performance of an algorithm under small random perturbations of that input. We measure this performance in terms of both the input size and the magnitude of the perturbations. We show that the simplex algorithm has polynomial smoothed complexity.
cs.DS↗
Smoothed Analysis of Interior-Point Algorithms: Termination
We perform a smoothed analysis of the termination phase of an interior-point method. By combining this analysis with the smoothed analysis of Renegar's interior-point algorithm by Dunagan, Spielman and Teng, we show that the smoothed complexity of an interior-point algorithm for linear programming is $O (m^{3} \log (m/σ))$. In contrast, the best known bound on the worst-case complexity of linear programming is $O (m^{3} L)$, where $L$ could be as large as $m$. We include an introduction to smoothed analysis and a tutorial on proof techniques that have been useful in smoothed analyses.
cs.DS↗
Smoothed analysis of algorithms
Spielman and Teng introduced the smoothed analysis of algorithms to provide a framework in which one could explain the success in practice of algorithms and heuristics that could not be understood through the traditional worst-case and average-case analyses. In this talk, we survey some of the smoothed analyses that have been performed.
math.OC↗
Regression Depth and Center Points
We show that, for any set of n points in d dimensions, there exists a hyperplane with regression depth at least ceiling(n/(d+1)). as had been conjectured by Rousseeuw and Hubert. Dually, for any arrangement of n hyperplanes in d dimensions there exists a point that cannot escape to infinity without crossing at least ceiling(n/(d+1)) hyperplanes. We also apply our approach to related questions on the existence of partitions of the data into subsets such that a common plane has nonzero regression depth in each subset, and to the computational complexity of regression depth problems.
cs.CG↗