arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.02774cs.DScs.LGmath.STstat.MLstat.TH
收藏

GMM 的稳健模型选择与近真学习

Robust Model Selection and Nearly-Proper Learning for GMMs

MIT(麻省理工学院);Microsoft Research(微软研究院)

Jerry Li, Allen Liu, Ankur Moitra

AI总结:

针对成分数未知且含对抗损坏的单变量 GMM,提出多项式时间稳健模型选择方法,以近线性成分数和近最优误差完成拟合,并推广至 Fourier-sparse 信号重建。

摘要:

在学习理论中,一个标准假设是数据由有限混合模型生成。但是,当成分数量事先未知时会发生什么?估计成分数量的问题也称为模型选择,其本身非常重要,但基本上不存在已知的、具有可证明保证的高效算法,更不用说能够容忍对抗性损坏的算法了。在本工作中,我们研究单变量高斯混合模型(GMM)的稳健模型选择问题。给定来自某个分布的 poly(k/ε) 个样本,而该分布在 TV 距离上与具有 k 个成分的 GMM 相距 ε,我们能够在 poly(k/ε) 时间内构造一个具有 \widetilde{O}(k) 个成分的 GMM,并以 \widetilde{O}(ε) 的误差逼近该分布。因此,我们能够在对数因子以内近似确定拟合该分布所需的最少成分数量。在我们的工作之前,用于学习任意单变量 GMM 的唯一已知算法,要么输出远多于 k 个成分(例如,核密度估计输出 k/ε^2 个成分),要么运行时间关于 k 呈指数增长。此外,通过调整我们的技术,我们在重建 Fourier-sparse 信号方面获得了类似结果。

英文摘要:

In learning theory, a standard assumption is that the data is generated from a finite mixture model. But what happens when the number of components is not known in advance? The problem of estimating the number of components, also called model selection, is important in its own right but there are essentially no known efficient algorithms with provable guarantees let alone ones that can tolerate adversarial corruptions. In this work, we study the problem of robust model selection for univariate Gaussian mixture models (GMMs). Given $\textsf{poly}(k/ε)$ samples from a distribution that is $ε$-close in TV distance to a GMM with $k$ components, we can construct a GMM with $\widetilde{O}(k)$ components that approximates the distribution to within $\widetilde{O}(ε)$ in $\textsf{poly}(k/ε)$ time. Thus we are able to approximately determine the minimum number of components needed to fit the distribution within a logarithmic factor. Prior to our work, the only known algorithms for learning arbitrary univariate GMMs either output significantly more than $k$ components (e.g. $k/ε^2$ components for kernel density estimates) or run in time exponential in $k$. Moreover, by adapting our techniques we obtain similar results for reconstructing Fourier-sparse signals.

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。

↑