每天一分钟,带你读遍机器人顶级会议文章
标题:Non-Convex Rank/Sparsity Regularization and Local Minima
作者:Carl Olsson, Marcus Carlsson, Fredrik Andersson, Viktor Larsson
来源:International Conference on Computer Vision (ICCV 2017)
播音员:格子
编译:杨雨生(35)
欢迎个人转发朋友圈;其他机构或自媒体如需转载,后台留言申请授权
摘要
本文研究的问题是,通过观察向量或者矩阵元素的线性组合,从而恢复一个低秩矩阵或者一个稀疏向量。
最新的方法采用L1范数或者核函数松弛的方法, 取代之前的非凸正则化方法。众所周知,如果所谓的有限等距性质(RIP)满足的话,这种方法几乎可以实现最优解。但另一方面,这种方法也存在收缩偏差(shrinking bias)现象,从而降低所求解的准确性。
本文中,我们研究一种可以避免这种偏差的可替代非凸正则化方法。由于当差别很大的时候,必然是高秩,我们的主要理论成果表明,如果RIP性质满足的话,可以很好的将静止点分离出来。因此,在初始值恰当的情况下,这种方法不会陷入一个局部最小值。我们的数值试验表明,即使是从一个随意初始值开始,这种方法也比标准的L1范数-或核范数-松弛方法更好的收敛。我们的试验结果同样可以用来验证我们方法的全局最优性。
Abstract
This paper considers the problem of recovering either a low rank matrix or a sparse vector from observations of linear combinations of the vector or matrix elements. Recent methods replace the non-convex regularization with L1 or nuclear norm relaxations. It is well known that this approach recovers near optimal solutions if a so called restricted isometry property (RIP) holds. On the other hand, it also has a shrinking bias which can degrade the solution. In this paper, we study an alternative non-convex regularization term that does not suffer from this bias. Our main theoretical results show that if a RIP holds then the stationary points are often well separated, in the sense that their differences must be of high cardinality/rank. Thus, with a suitable initial solution the approach is unlikely to fall into a bad local minimum. Our numerical tests show that the approach is likely to converge to a better solution than standard L1/nuclear-norm relaxation even when starting from trivial initializations. In many cases our results can also be used to verify global optimality of our method.
如果你对本文感兴趣,想要下载完整文章进行阅读,可以关注【泡泡机器人SLAM】公众号(paopaorobot_slam)。
欢迎来到泡泡论坛,这里有大牛为你解答关于SLAM的任何疑惑。
有想问的问题,或者想刷帖回答问题,泡泡论坛欢迎你!
泡泡网站:www.paopaorobot.org
泡泡论坛:http://paopaorobot.org/forums/
泡泡机器人SLAM的原创内容均由泡泡机器人的成员花费大量心血制作而成,希望大家珍惜我们的劳动成果,转载请务必注明出自【泡泡机器人SLAM】微信公众号,否则侵权必究!同时,我们也欢迎各位转载到自己的朋友圈,让更多的人能进入到SLAM这个领域中,让我们共同为推进中国的SLAM事业而努力!
商业合作及转载请联系liufuqiang_robot@hotmail.com