首页/论文/2005.06006

arXiv 2005.060062020-05math.STstat.MEstat.TH

High Probability Lower Bounds for the Total Variation Distance

Loris Michel, Jeffrey Näf, Nicolai Meinshausen

英文摘要：

The statistics and machine learning communities have recently seen a growing interest in classification-based approaches to two-sample testing. The outcome of a classification-based two-sample test remains a rejection decision, which is not always informative since the null hypothesis is seldom strictly true. Therefore, when a test rejects, it would be beneficial to provide an additional quantity serving as a refined measure of distributional difference. In this work, we introduce a framework for the construction of high-probability lower bounds on the total variation distance. These bounds are based on a one-dimensional projection, such as a classification or regression method, and can be interpreted as the minimal fraction of samples pointing towards a distributional difference. We further derive asymptotic power and detection rates of two proposed estimators and discuss potential uses through an application to a reanalysis climate dataset.

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。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

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。

继续探索

相关论文

Synthesis and analysis in total variation regularization

We generalize the bridge between analysis and synthesis estimators by Elad, Milanfar and Rubinstein (2007) to rank deficient cases. This is a starting point for the study of the connection between analysis and synthesis for total variation regularized estimators. In particular, the case of first order total variation regularized estimators over general graphs and their synthesis form are studied. We give a definition of the discrete graph derivative operator based on the notion of line graph and provide examples of the synthesis form of $k^{\text{th}}$ order total variation regularized estimat…

2019-01-18math.STstat.TH

可互换阵列的全变差界

Sharp Total Variation Bounds for Finitely Exchangeable Arrays

在这篇文章中，我们证明了可交换阵列和可交换序列之间的关系。然后，我们推导出尖锐的界限上的全变差分布之间的距离，无限可交换阵列。

2016-02-24math.PRmath.STstat.TH

两个二重Wiener-Itô积分之间的全变差距离

Total variation distance between two double Wiener-Itô integrals

利用Nourdin和Poly最近提出的一种方法，改进了Davydov和Martynova提出的两个双Wiener-Itô积分之间的全变差距离不等式的速度.应用程序的收敛速率的功能的相关二维分数布朗运动对Rosenblatt随机变量，然后给出，由Maejima和都铎以前的研究。

2013-05-22math.STstat.TH

全变差去噪的最优速率

Optimal rates for total variation denoising

其实际成功的动机，我们表明，二维全变差降噪满足尖锐的预言不等式，导致接近最佳的估计率为一大类的图像模型，如双保序，Hölder平滑和卡通。我们的分析取决于二维网格的非规范化拉普拉斯算子的属性，例如特征向量离域和谱衰减。我们还提出了扩展到两个以上的维度以及其他几个图形。

2016-06-16math.STstat.TH

On Rapid Variation of Multivariate Probability Densities

Multivariate rapid variation describes decay rates of joint light tails of a multivariate distribution. We impose a local uniformity condition to control decay variation of distribution tails along different directions, and using higher-order tail dependence of copulas, we prove that a rapidly varying multivariate density implies rapid variation of the joint distribution tails. As a corollary, rapid variation of skew-elliptical distributions is established under the assumption that the underlying density generators belong to the max-domain of attraction of the Gumbel distribution.

2021-04-29math.PRmath.STstat.TH

去偏恢复算法：应用于全变差和非局部均值

On debiasing restoration algorithms: applications to total-variation and nonlocal-means

图像恢复算法中的偏差可能妨碍进一步分析，通常当强度具有感兴趣的物理意义时，例如，在医学成像中。我们建议抑制一部分偏差-方法偏差-而保持不变的其他不可避免的部分-模型偏差。我们的去偏技术可以用于任何局部仿射估计，包括<$1正则化，各向异性全变差和一些非局部滤波器。

2015-03-05math.STstat.TH

更多相关论文收起更多论文

Oracle inequalities for square root analysis estimators with application to total variation penalties

Through the direct study of the analysis estimator we derive oracle inequalities with fast and slow rates by adapting the arguments involving projections by Dalalyan, Hebiri and Lederer (2017). We then extend the theory to the square root analysis estimator. Finally, we focus on (square root) total variation regularized estimators on graphs and obtain constant-friendly rates, which, up to log-terms, match previous results obtained by entropy calculations. We also obtain an oracle inequality for the (square root) total variation regularized estimator over the cycle graph.

2019-12-14math.STstat.MLstat.TH

Total variation distance for discretely observed Lévy processes: a Gaussian approximation of the small jumps

It is common practice to treat small jumps of Lévy processes as Wiener noise and thus to approximate its marginals by a Gaussian distribution. However, results that allow to quantify the goodness of this approximation according to a given metric are rare. In this paper, we clarify what happens when the chosen metric is the total variation distance. Such a choice is motivated by its statistical interpretation. If the total variation distance between two statistical models converges to zero, then no tests can be constructed to distinguish the two models which are therefore equivalent, statistica…

2019-04-02math.PRmath.STstat.TH

Adaptive Rates for Total Variation Image Denoising

We study the theoretical properties of image denoising via total variation penalized least-squares. We define the total vatiation in terms of the two-dimensional total discrete derivative of the image and show that it gives rise to denoised images that are piecewise constant on rectangular sets. We prove that, if the true image is piecewise constant on just a few rectangular sets, the denoised image converges to the true image at a parametric rate, up to a log factor. More generally, we show that the denoised image enjoys oracle properties, that is, it is almost as good as if some aspects of t…

2021-01-26math.STstat.MLstat.TH

Lower Bounds for the Total Variation Distance Given Means and Variances of Distributions

For arbitrary two probability measures on real d-space with given means and variances (covariance matrices), we provide lower bounds for their total variation distance. In the one-dimensional case, a tight bound is given.

2022-12-26cs.ITcs.LGmath.IT

Wasserstein与Lévy过程边缘间的全变差距离

Wasserstein and total variation distance between marginals of Lévy processes

我们提出了Wasserstein距离的上界顺序$p$之间的边缘的Lévy过程，包括高斯近似跳跃的无限活动。利用卷积结构，我们进一步得到了Lévy过程的边缘之间的全变差距离的上界。建立了与Zolotarev和Toscani-Fourier距离等其他度量的连接。具体的例子和应用程序的统计下界的理论说明。

2018-07-16math.PRmath.STstat.TH

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

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。

2016-05-26math.STstat.MLstat.TH

概率测度变化导致的期望变差

Variations on the Expectation due to Changes in the Probability Measure

INRIA, Centre Inria d’Université Côte d’Azur, Sophia Antipolis, France（INRIA，法国尼斯大学海岸校区Sophia Antipolis分校）；ECE Dept. Princeton University（普林斯顿大学电子工程系）；Laboratoire GAATI, University of French Polynesia（法属波利尼西亚大学GAATI实验室）

本文推导了概率测度变化引起函数期望变差的闭式表达式，并揭示了其与Gibbs概率测度、互信息及lautum信息的内在联系。

2025-04-27cs.ITcs.LGmath.IT

Lower Bounds on the Total Variation Distance Between Mixtures of Two Gaussians

Northwestern University（西北大学）；Halicioǧlu Data Science Institute, UC San Diego（加州大学圣地亚哥分校哈利西奥卢数据科学研究所）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；UC San Diego（加州大学圣地亚哥分校）

Mixtures of high dimensional Gaussian distributions have been studied extensively in statistics and learning theory. While the total variation distance appears naturally in the sample complexity of distribution learning, it is analytically difficult to obtain tight lower bounds for mixtures. Exploiting a connection between total variation distance and the characteristic function of the mixture, we provide fairly tight functional approximations. This enables us to derive new lower bounds on the total variation distance between pairs of two-component Gaussian mixtures that have a shared covarian…

2022-03-09cs.ITcs.LGmath.IT

任意$f$的一个下界--关于全变差的散度

A Lower Bound on Arbitrary $f$--Divergences in Terms of the Total Variation

量化两个概率测度相似性的一个重要工具是f-散度，它在统计学和信息论中有着广泛的应用。一个例子是全变差，它在f-发散中起着特殊的作用。证明了每一个f-散度都是由全变差的单调函数从下而上有界的。在适当的正则性条件下，该函数是单调的。注：主命题的证明相对容易，因此结果很可能是已知的。作者将非常感谢任何有关参考资料或相关工作的信息。

2009-03-10cs.ITmath.ITmath.PR