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 1605.08400math.STstat.MLstat.TH
收藏

1d以上的全变差类:极大极小率和线性平滑器的局限性

Total Variation Classes Beyond 1d: Minimax Rates, and the Limitations of Linear Smoothers

Veeranjaneyulu Sadhanala, Yu-Xiang Wang, Ryan Tibshirani

摘要:

我们考虑在$d$维网格(所有边长等于$n^{1/d}$)上的$n$位置上定义的函数的估计问题。当函数被约束为具有由$C_n$约束的离散全变差时,我们推导出由$n$和$C_n$参数化的极小极大最优(平方)$\ell_2$估计误差率。全变差去噪,也称为融合套索,被认为是速率最优的。存在几个更简单的估计,如拉普拉斯平滑和拉普拉斯特征映射。一个自然的问题是:这些更简单的估计器能表现得一样好吗?我们证明了这些估计,更广泛地说,所有的输入数据的线性变换估计,是次优的有界变差的函数类。这将Donoho和Johnstone [1998]关于1维全变差空间的基本发现扩展到了更高维。这意味着计算上更简单的方法不能用于这样复杂的去噪任务,而不牺牲统计精度。我们还推导出$d$维网格上离散Sobolev空间的极大极小率,在某种意义上,它小于全变差函数空间。事实上,这些空间足够小,线性估计可以是最佳的-一些著名的,如拉普拉斯平滑和拉普拉斯特征映射,正如我们所展示的。最后,我们研究了全变差去噪器对这些较小的Sobolev函数空间的自适应性问题。

英文摘要:

We consider the problem of estimating a function defined over $n$ locations on a $d$-dimensional grid (having all side lengths equal to $n^{1/d}$). When the function is constrained to have discrete total variation bounded by $C_n$, we derive the minimax optimal (squared) $\ell_2$ estimation error rate, parametrized by $n$ and $C_n$. Total variation denoising, also known as the fused lasso, is seen to be rate optimal. Several simpler estimators exist, such as Laplacian smoothing and Laplacian eigenmaps. A natural question is: can these simpler estimators perform just as well? We prove that these estimators, and more broadly all estimators given by linear transformations of the input data, are suboptimal over the class of functions with bounded variation. This extends fundamental findings of Donoho and Johnstone [1998] on 1-dimensional total variation spaces to higher dimensions. The implication is that the computationally simpler methods cannot be used for such sophisticated denoising tasks, without sacrificing statistical accuracy. We also derive minimax rates for discrete Sobolev spaces over $d$-dimensional grids, which are, in some sense, smaller than the total variation function spaces. Indeed, these are small enough spaces that linear estimators can be optimal---and a few well-known ones are, such as Laplacian smoothing and Laplacian eigenmaps, as we show. Lastly, we investigate the problem of adaptivity of the total variation denoiser to these smaller Sobolev function spaces.

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。

↑