Convex Coding

Convex Coding
复制标题

DOI:
--
复制
发表时间:
2009-06
期刊:
--
影响因子:
--
通讯作者:
David M. Bradley;J. Bagnell
David M. Bradley;J. Bagnell
中科院分区:
其他
文献类型:
--
作者:
David M. Bradley;J. Bagnell

文献摘要

被引文献

相似文献

受最近关于聚类凸公式的工作的启发(Lashkari & Golland,2008; Nowozin & Bakir,2008),我们研究了稀疏编码问题的新公式(Olshausen & Field,1997)。在稀疏编码中,我们试图同时稀疏地表示数据向量序列(即稀疏近似(Tropp等人,2006)),同时还找到能够实现这种近似的代码。由于现有的稀疏编码交替优化过程在理论上容易出现严重的局部极小问题,我们提出了一种稀疏编码问题的凸松弛,并推导出一种提升式算法,(Nowozin & Bakir,2008)作为一个凸的“主问题”,它称为(潜在的非凸)子问题,以确定下一个代码元素添加。最后,我们展示了我们的提升编码算法的图像去噪任务的属性。
Inspired by recent work on convex formulations of clustering (Lashkari & Golland, 2008; Nowozin & Bakir, 2008) we investigate a new formulation of the Sparse Coding Problem (Olshausen & Field, 1997). In sparse coding we attempt to simultaneously represent a sequence of data-vectors sparsely (i.e. sparse approximation (Tropp et al., 2006)) in terms of a "code" defined by a set of basis elements, while also finding a code that enables such an approximation. As existing alternating optimization procedures for sparse coding are theoretically prone to severe local minima problems, we propose a convex relaxation of the sparse coding problem and derive a boosting-style algorithm, that (Nowozin & Bakir, 2008) serves as a convex "master problem" which calls a (potentially non-convex) sub-problem to identify the next code element to add. Finally, we demonstrate the properties of our boosted coding algorithm on an image denoising task.