How well do local algorithms solve semidefinite programs?
How well do local algorithms solve semidefinite programs?
复制标题
局部算法求解半定程序的效果如何?
DOI:
10.1145/3055399.3055451
复制
发表时间:
2017
期刊:
影响因子:
--
通讯作者:
Montanari, Andrea
中科院分区:
文献类型:
--
作者:
Fan, Zhou;Montanari, Andrea
Several probabilistic models from high-dimensional statistics and machine learning reveal an intriguing and yet poorly understood dichotomy. Either simple local algorithms succeed in estimating the object of interest, or even sophisticated semi-definite programming (SDP) relaxations fail. In order to explore this phenomenon, we study a classical SDP relaxation of the minimum graph bisection problem, when applied to Erdos-Renyi random graphs with bounded average degree d > 1, and obtain several types of results. First, we use a dual witness construction (using the so-called non-backtracking matrix of the graph) to upper bound the SDP value. Second, we prove that a simple local algorithm approximately solves the SDP to within a factor 2d^2/(2d^2 + d - 1) of the upper bound. In particular, the local algorithm is at most 8/9 suboptimal, and 1 + O(d^-1) suboptimal for large degree.We then analyze a more sophisticated local algorithm, which aggregates information according to the harmonic measure on the limiting Galton-Watson (GW) tree. The resulting lower bound is expressed in terms of the conductance of the GW tree and matches surprisingly well the empirically determined SDP values on large-scale Erdos-Renyi graphs.We finally consider the planted partition model. In this case, purely local algorithms are known to fail, but they do succeed if a small amount of side information is available. Our results imply quantitative bounds on the threshold for partial recovery using SDP in this model.
登录
查看更多内容
影响因子:
1.6
作者:
A. Montanari
通讯作者:
A. Montanari
影响因子:
2.5
作者:
Hajek, Bruce;Wu, Yihong;Xu, Jiaming
通讯作者:
Xu, Jiaming
DOI:
10.1007/978-1-4612-1862-3_18
发表时间:
1997
期刊:
Combinatorics, Probability and Computing
影响因子:
--
作者:
R. Lyons;Robin Pemantle;Y. Peres
通讯作者:
Y. Peres
DOI:
--
发表时间:
2008
期刊:
Comb.
影响因子:
--
作者:
G. Elek
通讯作者:
G. Elek
影响因子:
2.3
作者:
Rahman, Mustazee;Virag, Balint
通讯作者:
Virag, Balint