正交统计学习和双机器学习已成为在存在滋扰成分的情况下,作为两阶段统计预测的一般框架。我们对具有满足自我符合性能的损失功能的正交统计学习方法的过量风险建立了非扰动界限。我们的界限在提升强凸度的假设时,通过维数因子来改善现有界限。我们用来自多个治疗效应估计的示例和广义部分线性建模来说明结果。
translated by 谷歌翻译
This paper revisits a fundamental problem in statistical inference from a non-asymptotic theoretical viewpoint $\unicode{x2013}$ the construction of confidence sets. We establish a finite-sample bound for the estimator, characterizing its asymptotic behavior in a non-asymptotic fashion. An important feature of our bound is that its dimension dependency is captured by the effective dimension $\unicode{x2013}$ the trace of the limiting sandwich covariance $\unicode{x2013}$ which can be much smaller than the parameter dimension in some regimes. We then illustrate how the bound can be used to obtain a confidence set whose shape is adapted to the optimization landscape induced by the loss function. Unlike previous works that rely heavily on the strong convexity of the loss function, we only assume the Hessian is lower bounded at optimum and allow it to gradually becomes degenerate. This property is formalized by the notion of generalized self-concordance which originated from convex optimization. Moreover, we demonstrate how the effective dimension can be estimated from data and characterize its estimation accuracy. We apply our results to maximum likelihood estimation with generalized linear models, score matching with exponential families, and hypothesis testing with Rao's score test.
translated by 谷歌翻译
Influence diagnostics such as influence functions and approximate maximum influence perturbations are popular in machine learning and in AI domain applications. Influence diagnostics are powerful statistical tools to identify influential datapoints or subsets of datapoints. We establish finite-sample statistical bounds, as well as computational complexity bounds, for influence functions and approximate maximum influence perturbations using efficient inverse-Hessian-vector product implementations. We illustrate our results with generalized linear models and large attention based models on synthetic and real data.
translated by 谷歌翻译
我们研究了称为“乐观速率”(Panchenko 2002; Srebro等,2010)的统一收敛概念,用于与高斯数据的线性回归。我们的精致分析避免了现有结果中的隐藏常量和对数因子,这已知在高维设置中至关重要,特别是用于了解插值学习。作为一个特殊情况,我们的分析恢复了Koehler等人的保证。(2021年),在良性过度的过度条件下,严格地表征了低规范内插器的人口风险。但是,我们的乐观速度绑定还分析了具有任意训练错误的预测因子。这使我们能够在随机设计下恢复脊和套索回归的一些经典统计保障,并有助于我们在过度参数化制度中获得精确了解近端器的过度风险。
translated by 谷歌翻译
我们考虑与高斯数据的高维线性回归中的插值学习,并在类高斯宽度方面证明了任意假设类别中的内插器的泛化误差。将通用绑定到欧几里德常规球恢复了Bartlett等人的一致性结果。(2020)对于最小规范内插器,并确认周等人的预测。(2020)在高斯数据的特殊情况下,对于近乎最小常态的内插器。我们通过将其应用于单位来证明所界限的一般性,从而获得最小L1-NORM Interpoolator(基础追踪)的新型一致性结果。我们的结果表明,基于规范的泛化界限如何解释并用于分析良性过度装备,至少在某些设置中。
translated by 谷歌翻译
当分别从$ \ mathfrak {l} $ - subgaussian分布和重尾分布中,分别采样协变量和噪声时,我们考虑了线性回归系数的鲁棒和稀疏估计,并由对抗性和噪音污染异常值。我们处理两种情况:协变量的已知或未知协方差。特别是在前一种情况下,我们的估计器几乎达到了信息理论上的最佳错误绑定,而我们的错误界限比以前处理类似情况的研究更明显。我们的估计分析在很大程度上依赖于通用链条来得出急剧的误差界限。
translated by 谷歌翻译
通过在线规范相关性分析的问题,我们提出了\ emph {随机缩放梯度下降}(SSGD)算法,以最小化通用riemannian歧管上的随机功能的期望。 SSGD概括了投影随机梯度下降的思想,允许使用缩放的随机梯度而不是随机梯度。在特殊情况下,球形约束的特殊情况,在广义特征向量问题中产生的,我们建立了$ \ sqrt {1 / t} $的令人反感的有限样本,并表明该速率最佳最佳,直至具有积极的积极因素相关参数。在渐近方面,一种新的轨迹平均争论使我们能够实现局部渐近常态,其速率与鲁普特 - Polyak-Quaditsky平均的速率匹配。我们将这些想法携带在一个在线规范相关分析,从事文献中的第一次获得了最佳的一次性尺度算法,其具有局部渐近融合到正常性的最佳一次性尺度算法。还提供了用于合成数据的规范相关分析的数值研究。
translated by 谷歌翻译
在因果推理和强盗文献中,基于观察数据的线性功能估算线性功能的问题是规范的。我们分析了首先估计治疗效果函数的广泛的两阶段程序,然后使用该数量来估计线性功能。我们证明了此类过程的均方误差上的非反应性上限:这些边界表明,为了获得非反应性最佳程序,应在特定加权$ l^2 $中最大程度地估算治疗效果的误差。 -规范。我们根据该加权规范的约束回归分析了两阶段的程序,并通过匹配非轴突局部局部最小值下限,在有限样品中建立了实例依赖性最优性。这些结果表明,除了取决于渐近效率方差之外,最佳的非质子风险除了取决于样本量支持的最富有函数类别的真实结果函数与其近似类别之间的加权规范距离。
translated by 谷歌翻译
我们在对数损失下引入条件密度估计的过程,我们调用SMP(样本Minmax预测器)。该估算器最大限度地减少了统计学习的新一般过度风险。在标准示例中,此绑定量表为$ d / n $,$ d $ d $模型维度和$ n $ sample大小,并在模型拼写条目下批判性仍然有效。作为一个不当(超出型号)的程序,SMP在模型内估算器(如最大似然估计)的内部估算器上,其风险过高的风险降低。相比,与顺序问题的方法相比,我们的界限删除了SubOltimal $ \ log n $因子,可以处理无限的类。对于高斯线性模型,SMP的预测和风险受到协变量的杠杆分数,几乎匹配了在没有条件的线性模型的噪声方差或近似误差的条件下匹配的最佳风险。对于Logistic回归,SMP提供了一种非贝叶斯方法来校准依赖于虚拟样本的概率预测,并且可以通过解决两个逻辑回归来计算。它达到了$ O的非渐近风险((d + b ^ 2r ^ 2)/ n)$,其中$ r $绑定了特征的规范和比较参数的$ B $。相比之下,在模型内估计器内没有比$ \ min达到更好的速率({b r} / {\ sqrt {n}},{d e ^ {br} / {n})$。这为贝叶斯方法提供了更实用的替代方法,这需要近似的后部采样,从而部分地解决了Foster等人提出的问题。 (2018)。
translated by 谷歌翻译
成功的深度学习模型往往涉及培训具有比训练样本数量更多的参数的神经网络架构。近年来已经广泛研究了这种超分子化的模型,并且通过双下降现象和通过优化景观的结构特性,从统计的角度和计算视角都建立了过分统计化的优点。尽管在过上分层的制度中深入学习架构的显着成功,但也众所周知,这些模型对其投入中的小对抗扰动感到高度脆弱。即使在普遍培训的情况下,它们在扰动输入(鲁棒泛化)上的性能也会比良性输入(标准概括)的最佳可达到的性能更糟糕。因此,必须了解如何从根本上影响稳健性的情况下如何影响鲁棒性。在本文中,我们将通过专注于随机特征回归模型(具有随机第一层权重的两层神经网络)来提供超分度化对鲁棒性的作用的精确表征。我们考虑一个制度,其中样本量,输入维度和参数的数量彼此成比例地生长,并且当模型发生前列地训练时,可以为鲁棒泛化误差导出渐近精确的公式。我们的发达理论揭示了过分统计化对鲁棒性的非竞争效果,表明对于普遍训练的随机特征模型,高度公正化可能会损害鲁棒泛化。
translated by 谷歌翻译
元学习或学习学习,寻求设计算法,可以利用以前的经验快速学习新技能或适应新环境。表示学习 - 用于执行元学习的关键工具 - 了解可以在多个任务中传输知识的数据表示,这在数据稀缺的状态方面是必不可少的。尽管最近在Meta-Leature的实践中感兴趣的兴趣,但缺乏元学习算法的理论基础,特别是在学习可转让陈述的背景下。在本文中,我们专注于多任务线性回归的问题 - 其中多个线性回归模型共享常见的低维线性表示。在这里,我们提供了可提供的快速,采样高效的算法,解决了(1)的双重挑战,从多个相关任务和(2)将此知识转移到新的,看不见的任务中的常见功能。两者都是元学习的一般问题的核心。最后,我们通过在学习这些线性特征的样本复杂性上提供信息定理下限来补充这些结果。
translated by 谷歌翻译
We study a natural extension of classical empirical risk minimization, where the hypothesis space is a random subspace of a given space. In particular, we consider possibly data dependent subspaces spanned by a random subset of the data, recovering as a special case Nystrom approaches for kernel methods. Considering random subspaces naturally leads to computational savings, but the question is whether the corresponding learning accuracy is degraded. These statistical-computational tradeoffs have been recently explored for the least squares loss and self-concordant loss functions, such as the logistic loss. Here, we work to extend these results to convex Lipschitz loss functions, that might not be smooth, such as the hinge loss used in support vector machines. This unified analysis requires developing new proofs, that use different technical tools, such as sub-gaussian inputs, to achieve fast rates. Our main results show the existence of different settings, depending on how hard the learning problem is, for which computational efficiency can be improved with no loss in performance.
translated by 谷歌翻译
截断的线性回归是统计学中的一个经典挑战,其中$ y = w^t x + \ varepsilon $及其相应的功能向量,$ x \ in \ mathbb {r}^k $,仅在当时才观察到标签属于某些子集$ s \ subseteq \ mathbb {r} $;否则,对$(x,y)$的存在被隐藏在观察中。以截断的观察结果的线性回归一直是其一般形式的挑战,因为〜\ citet {tobin1958估计,amemiya1973 reflecression}的早期作品。当误差的分布与已知方差正常时,〜\ citet {daskalakis2019 truncatedRegerse}的最新工作在线性模型$ w $上提供了计算和统计上有效的估计器。在本文中,当噪声方差未知时,我们为截断的线性回归提供了第一个计算和统计上有效的估计器,同时估计了噪声的线性模型和方差。我们的估计器基于对截短样品的负模样中的预测随机梯度下降的有效实施。重要的是,我们表明我们的估计错误是渐近正常的,我们使用它来为我们的估计提供明确的置信区域。
translated by 谷歌翻译
神经网络模型的最新成功揭示了一种令人惊讶的统计现象:完全拟合噪声数据的统计模型可以很好地推广到看不见的测试数据。了解$ \ textit {良性过拟合} $的这种现象吸引了强烈的理论和经验研究。在本文中,我们考虑插值两层线性神经网络在平方损失上梯度流训练,当协变量满足亚高斯和抗浓度的特性时,在平方损耗上训练,并在多余的风险上获得界限,并且噪声是独立和次级高斯的。。通过利用最新的结果来表征该估计器的隐性偏见,我们的边界强调了初始化质量的作用以及数据协方差矩阵在实现低过量风险中的特性。
translated by 谷歌翻译
我们提出了一种基于优化的基于优化的框架,用于计算差异私有M估算器以及构建差分私立置信区的新方法。首先,我们表明稳健的统计数据可以与嘈杂的梯度下降或嘈杂的牛顿方法结合使用,以便分别获得具有全局线性或二次收敛的最佳私人估算。我们在局部强大的凸起和自我协调下建立当地和全球融合保障,表明我们的私人估算变为对非私人M估计的几乎最佳附近的高概率。其次,我们通过构建我们私有M估计的渐近方差的差异私有估算来解决参数化推断的问题。这自然导致近​​似枢轴统计,用于构建置信区并进行假设检测。我们展示了偏置校正的有效性,以提高模拟中的小样本实证性能。我们说明了我们在若干数值例子中的方法的好处。
translated by 谷歌翻译
We consider the problem of estimating the optimal transport map between a (fixed) source distribution $P$ and an unknown target distribution $Q$, based on samples from $Q$. The estimation of such optimal transport maps has become increasingly relevant in modern statistical applications, such as generative modeling. At present, estimation rates are only known in a few settings (e.g. when $P$ and $Q$ have densities bounded above and below and when the transport map lies in a H\"older class), which are often not reflected in practice. We present a unified methodology for obtaining rates of estimation of optimal transport maps in general function spaces. Our assumptions are significantly weaker than those appearing in the literature: we require only that the source measure $P$ satisfies a Poincar\'e inequality and that the optimal map be the gradient of a smooth convex function that lies in a space whose metric entropy can be controlled. As a special case, we recover known estimation rates for bounded densities and H\"older transport maps, but also obtain nearly sharp results in many settings not covered by prior work. For example, we provide the first statistical rates of estimation when $P$ is the normal distribution and the transport map is given by an infinite-width shallow neural network.
translated by 谷歌翻译
High-dimensional data can often display heterogeneity due to heteroscedastic variance or inhomogeneous covariate effects. Penalized quantile and expectile regression methods offer useful tools to detect heteroscedasticity in high-dimensional data. The former is computationally challenging due to the non-smooth nature of the check loss, and the latter is sensitive to heavy-tailed error distributions. In this paper, we propose and study (penalized) robust expectile regression (retire), with a focus on iteratively reweighted $\ell_1$-penalization which reduces the estimation bias from $\ell_1$-penalization and leads to oracle properties. Theoretically, we establish the statistical properties of the retire estimator under two regimes: (i) low-dimensional regime in which $d \ll n$; (ii) high-dimensional regime in which $s\ll n\ll d$ with $s$ denoting the number of significant predictors. In the high-dimensional setting, we carefully characterize the solution path of the iteratively reweighted $\ell_1$-penalized retire estimation, adapted from the local linear approximation algorithm for folded-concave regularization. Under a mild minimum signal strength condition, we show that after as many as $\log(\log d)$ iterations the final iterate enjoys the oracle convergence rate. At each iteration, the weighted $\ell_1$-penalized convex program can be efficiently solved by a semismooth Newton coordinate descent algorithm. Numerical studies demonstrate the competitive performance of the proposed procedure compared with either non-robust or quantile regression based alternatives.
translated by 谷歌翻译
随机梯度下降(SGD)已被证明在许多深度学习应用中都很好地概括了。在实践中,人们经常以几何衰减的步骤运行SGD,即,恒定的初始步骤,然后是多个几何步骤衰减,并将最后一个迭代用作输出。已知这种SGD几乎对经典有限维线性回归问题几乎是最佳的(Ge等,2019)。但是,在过度参数化设置中对SGD的最后一次迭代进行了彻底的分析。在本文中,我们对SGD的最后一个迭代风险界限进行了依赖问题的分析,并具有腐烂的步骤,以(过度参数化)线性回归问题。特别是,对于带有(尾部)几何衰减步骤的最后迭代SGD,我们证明了多余风险的上限和下限几乎匹配。此外,我们为最后一次迭代的SGD提供了多余的风险下限,并以多项式衰减的步骤进行了大小,并以实例的方式证明了几何腐烂的步骤的优势,这补充了先前工作中的最小值比较。
translated by 谷歌翻译
我们考虑通过流算法从单个轨迹估计线性时间不变(LTI)动态系统的问题,这在包括增强学习(RL)和时间序列分析的若干应用中遇到。虽然LTI系统估计问题在{\ em离线}设置中进行了很好地研究,但实际上重要的流媒体/在线设置很少受到关注。如随机梯度下降(SGD)等标准流动方法不太可能起作用,因为流点可以高度相关。在这项工作中,我们提出了一种新颖的流媒体算法,SGD具有反向体验的重播($ \ MATHSF {SGD} - \ MATHSF {RER),这是由RL文献中流行的体验重播(ER)技术的启发。 $ \ mathsf {sgd} - \ mathsf {rer} $划分为小缓冲区,并在存储在单个缓冲区中的数据后向后运行SGD。我们表明该算法精确地解构了依赖结构,并获得了从理论上最佳保证的信息,用于参数误差和预测误差。因此,我们提供了我们的第一至最佳的知识 - 最佳的SGD风格算法,用于使用一阶Oracle的线性系统识别的经典问题。此外,$ \ mathsf {sgd} - \ mathsf {rer} $可以应用于具有已知稀疏模式和非线性动态系统的稀疏LTI识别的更多常规设置。我们的工作表明,数据依赖性结构的知识可以帮助我们在统计上和计算上的算法设计中,这些算法可以“去相关”流样本。
translated by 谷歌翻译
Classical asymptotic theory for statistical inference usually involves calibrating a statistic by fixing the dimension $d$ while letting the sample size $n$ increase to infinity. Recently, much effort has been dedicated towards understanding how these methods behave in high-dimensional settings, where $d$ and $n$ both increase to infinity together. This often leads to different inference procedures, depending on the assumptions about the dimensionality, leaving the practitioner in a bind: given a dataset with 100 samples in 20 dimensions, should they calibrate by assuming $n \gg d$, or $d/n \approx 0.2$? This paper considers the goal of dimension-agnostic inference; developing methods whose validity does not depend on any assumption on $d$ versus $n$. We introduce an approach that uses variational representations of existing test statistics along with sample splitting and self-normalization to produce a new test statistic with a Gaussian limiting distribution, regardless of how $d$ scales with $n$. The resulting statistic can be viewed as a careful modification of degenerate U-statistics, dropping diagonal blocks and retaining off-diagonal blocks. We exemplify our technique for some classical problems including one-sample mean and covariance testing, and show that our tests have minimax rate-optimal power against appropriate local alternatives. In most settings, our cross U-statistic matches the high-dimensional power of the corresponding (degenerate) U-statistic up to a $\sqrt{2}$ factor.
translated by 谷歌翻译