arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0902.1284cs.LG
收藏

基于压缩感知的多标签预测

Multi-Label Prediction via Compressed Sensing

UC San Diego(加州大学圣地亚哥分校);TTI-Chicago(芝加哥丰田技术研究院);Rutgers University(罗格斯大学)

Daniel Hsu, Sham M. Kakade, John Langford, Tong Zhang

摘要:

我们考虑多标签预测问题与大的输出空间的假设下,输出稀疏-目标(标签)向量有小的支持。我们开发了一个通用的理论流行的纠错输出编码方案的一个变体,利用压缩感知的思想,利用这种稀疏性。该方法可以看作是一个简单的减少从多标签回归问题的二元回归问题。我们表明,子问题的数量只需要对数的可能的标签的总数,使这种方法从根本上比其他更有效。我们还以遗憾变换界限(一般)的形式陈述并证明了该方法的鲁棒性保证,并且还提供了对线性预测设置的更详细分析。

英文摘要:

We consider multi-label prediction problems with large output spaces under the assumption of output sparsity -- that the target (label) vectors have small support. We develop a general theory for a variant of the popular error correcting output code scheme, using ideas from compressed sensing for exploiting this sparsity. The method can be regarded as a simple reduction from multi-label regression problems to binary regression problems. We show that the number of subproblems need only be logarithmic in the total number of possible labels, making this approach radically more efficient than others. We also state and prove robustness guarantees for this method in the form of regret transform bounds (in general), and also provide a more detailed analysis for the linear prediction setting.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑