深入学习在现代分类任务中取得了许多突破。已经提出了众多架构用于不同的数据结构,但是当涉及丢失功能时,跨熵损失是主要的选择。最近,若干替代损失已经看到了深度分类器的恢复利益。特别是,经验证据似乎促进了方形损失,但仍然缺乏理论效果。在这项工作中,我们通过系统地研究了在神经切线内核(NTK)制度中的过度分化的神经网络的表现方式来促进对分类方面损失的理论理解。揭示了关于泛化误差,鲁棒性和校准错误的有趣特性。根据课程是否可分离,我们考虑两种情况。在一般的不可分类案例中,为错误分类率和校准误差建立快速收敛速率。当类是可分离的时,错误分类率改善了速度快。此外,经过证明得到的余量被证明是低于零的较低,提供了鲁棒性的理论保证。我们希望我们的调查结果超出NTK制度并转化为实际设置。为此,我们对实际神经网络进行广泛的实证研究,展示了合成低维数据和真实图像数据中方损的有效性。与跨熵相比,方形损耗具有可比的概括误差,但具有明显的鲁棒性和模型校准的优点。
translated by 谷歌翻译
We introduce a tunable loss function called $\alpha$-loss, parameterized by $\alpha \in (0,\infty]$, which interpolates between the exponential loss ($\alpha = 1/2$), the log-loss ($\alpha = 1$), and the 0-1 loss ($\alpha = \infty$), for the machine learning setting of classification. Theoretically, we illustrate a fundamental connection between $\alpha$-loss and Arimoto conditional entropy, verify the classification-calibration of $\alpha$-loss in order to demonstrate asymptotic optimality via Rademacher complexity generalization techniques, and build-upon a notion called strictly local quasi-convexity in order to quantitatively characterize the optimization landscape of $\alpha$-loss. Practically, we perform class imbalance, robustness, and classification experiments on benchmark image datasets using convolutional-neural-networks. Our main practical conclusion is that certain tasks may benefit from tuning $\alpha$-loss away from log-loss ($\alpha = 1$), and to this end we provide simple heuristics for the practitioner. In particular, navigating the $\alpha$ hyperparameter can readily provide superior model robustness to label flips ($\alpha > 1$) and sensitivity to imbalanced classes ($\alpha < 1$).
translated by 谷歌翻译
尽管使用对抗性训练捍卫深度学习模型免受对抗性扰动的经验成功,但到目前为止,仍然不清楚对抗性扰动的存在背后的原则是什么,而对抗性培训对神经网络进行了什么来消除它们。在本文中,我们提出了一个称为特征纯化的原则,在其中,我们表明存在对抗性示例的原因之一是在神经网络的训练过程中,在隐藏的重量中积累了某些小型密集混合物;更重要的是,对抗训练的目标之一是去除此类混合物以净化隐藏的重量。我们介绍了CIFAR-10数据集上的两个实验,以说明这一原理,并且一个理论上的结果证明,对于某些自然分类任务,使用随机初始初始化的梯度下降训练具有RELU激活的两层神经网络确实满足了这一原理。从技术上讲,我们给出了我们最大程度的了解,第一个结果证明,以下两个可以同时保持使用RELU激活的神经网络。 (1)对原始数据的训练确实对某些半径的小对抗扰动确实不舒适。 (2)即使使用经验性扰动算法(例如FGM),实际上也可以证明对对抗相同半径的任何扰动也可以证明具有强大的良好性。最后,我们还证明了复杂性的下限,表明该网络的低复杂性模型,例如线性分类器,低度多项式或什至是神经切线核,无论使用哪种算法,都无法防御相同半径的扰动训练他们。
translated by 谷歌翻译
众所周知,现代神经网络容易受到对抗例子的影响。为了减轻这个问题,已经提出了一系列强大的学习算法。但是,尽管通过某些方法可以通过某些方法接近稳定的训练误差,但所有现有的算法都会导致较高的鲁棒概括误差。在本文中,我们从深层神经网络的表达能力的角度提供了对这种令人困惑的现象的理论理解。具体而言,对于二进制分类数据,我们表明,对于Relu网络,虽然轻度的过度参数足以满足较高的鲁棒训练精度,但存在持续的稳健概括差距,除非神经网络的大小是指数的,却是指数的。数据维度$ d $。即使数据是线性可分离的,这意味着要实现低清洁概括错误很容易,我们仍然可以证明$ \ exp({\ omega}(d))$下限可用于鲁棒概括。通常,只要它们的VC维度最多是参数数量,我们的指数下限也适用于各种神经网络家族和其他功能类别。此外,我们为网络大小建立了$ \ exp({\ mathcal {o}}(k))$的改进的上限,当数据放在具有内在尺寸$ k $的歧管上时,以实现低鲁棒的概括错误($) k \ ll d $)。尽管如此,我们也有一个下限,相对于$ k $成倍增长 - 维度的诅咒是不可避免的。通过证明网络大小之间的指数分离以实现较低的鲁棒训练和泛化错误,我们的结果表明,鲁棒概括的硬度可能源于实用模型的表现力。
translated by 谷歌翻译
We explore the ability of overparameterized shallow ReLU neural networks to learn Lipschitz, non-differentiable, bounded functions with additive noise when trained by Gradient Descent (GD). To avoid the problem that in the presence of noise, neural networks trained to nearly zero training error are inconsistent in this class, we focus on the early-stopped GD which allows us to show consistency and optimal rates. In particular, we explore this problem from the viewpoint of the Neural Tangent Kernel (NTK) approximation of a GD-trained finite-width neural network. We show that whenever some early stopping rule is guaranteed to give an optimal rate (of excess risk) on the Hilbert space of the kernel induced by the ReLU activation function, the same rule can be used to achieve minimax optimal rate for learning on the class of considered Lipschitz functions by neural networks. We discuss several data-free and data-dependent practically appealing stopping rules that yield optimal rates.
translated by 谷歌翻译
这项工作表征了深度对线性回归优化景观的影响,表明尽管具有非凸性,但更深的模型具有更理想的优化景观。我们考虑了一个健壮且过度参数化的设置,其中测量的子集严重损坏了噪声,真正的线性模型将通过$ n $ layer-layer线性神经网络捕获。在负面方面,我们表明这个问题\ textit {do}具有良性景观:给定任何$ n \ geq 1 $,具有恒定概率,存在与既不是本地也不是全局最小值的地面真理的解决方案。但是,从积极的一面来看,我们证明,对于具有$ n \ geq 2 $的任何$ n $ layer模型,一种简单的次级方法变得忽略了这种``有问题的''解决方案;取而代之的是,它收敛于平衡的解决方案,该解决方案不仅接近地面真理,而且享有平坦的当地景观,从而避免了“早期停止”的需求。最后,我们从经验上验证了更深层模型的理想优化格局扩展到其他强大的学习任务,包括具有$ \ ell_1 $ -loss的深层矩阵恢复和深度relu网络。
translated by 谷歌翻译
This paper investigates the stability of deep ReLU neural networks for nonparametric regression under the assumption that the noise has only a finite p-th moment. We unveil how the optimal rate of convergence depends on p, the degree of smoothness and the intrinsic dimension in a class of nonparametric regression functions with hierarchical composition structure when both the adaptive Huber loss and deep ReLU neural networks are used. This optimal rate of convergence cannot be obtained by the ordinary least squares but can be achieved by the Huber loss with a properly chosen parameter that adapts to the sample size, smoothness, and moment parameters. A concentration inequality for the adaptive Huber ReLU neural network estimators with allowable optimization errors is also derived. To establish a matching lower bound within the class of neural network estimators using the Huber loss, we employ a different strategy from the traditional route: constructing a deep ReLU network estimator that has a better empirical loss than the true function and the difference between these two functions furnishes a low bound. This step is related to the Huberization bias, yet more critically to the approximability of deep ReLU networks. As a result, we also contribute some new results on the approximation theory of deep ReLU neural networks.
translated by 谷歌翻译
在本文中,我们利用过度参数化来设计高维单索索引模型的无规矩算法,并为诱导的隐式正则化现象提供理论保证。具体而言,我们研究了链路功能是非线性且未知的矢量和矩阵单索引模型,信号参数是稀疏向量或低秩对称矩阵,并且响应变量可以是重尾的。为了更好地理解隐含正规化的角色而没有过度的技术性,我们假设协变量的分布是先验的。对于载体和矩阵设置,我们通过采用分数函数变换和专为重尾数据的强大截断步骤来构造过度参数化最小二乘损耗功能。我们建议通过将无规则化的梯度下降应用于损耗函数来估计真实参数。当初始化接近原点并且步骤中足够小时,我们证明了所获得的解决方案在载体和矩阵案件中实现了最小的收敛统计速率。此外,我们的实验结果支持我们的理论调查结果,并表明我们的方法在$ \ ell_2 $ -staticatisticated率和变量选择一致性方面具有明确的正则化的经验卓越。
translated by 谷歌翻译
我们证明了由例如He等人提出的广泛使用的方法。(2015年)并使用梯度下降对最小二乘损失进行训练并不普遍。具体而言,我们描述了一大批一维数据生成分布,较高的概率下降只会发现优化景观的局部最小值不好,因为它无法将其偏离偏差远离其初始化,以零移动。。事实证明,在这些情况下,即使目标函数是非线性的,发现的网络也基本执行线性回归。我们进一步提供了数值证据,表明在实际情况下,对于某些多维分布而发生这种情况,并且随机梯度下降表现出相似的行为。我们还提供了有关初始化和优化器的选择如何影响这种行为的经验结果。
translated by 谷歌翻译
过度分化的深网络的泛化神秘具有有动力的努力,了解梯度下降(GD)如何收敛到概括井的低损耗解决方案。现实生活中的神经网络从小随机值初始化,并以分类的“懒惰”或“懒惰”或“NTK”的训练训练,分析更成功,以及最近的结果序列(Lyu和Li ,2020年; Chizat和Bach,2020; Ji和Telgarsky,2020)提供了理论证据,即GD可以收敛到“Max-ramin”解决方案,其零损失可能呈现良好。但是,仅在某些环境中证明了余量的全球最优性,其中神经网络无限或呈指数级宽。目前的纸张能够为具有梯度流动训练的两层泄漏的Relu网,无论宽度如何,都能为具有梯度流动的双层泄漏的Relu网建立这种全局最优性。分析还为最近的经验研究结果(Kalimeris等,2019)给出了一些理论上的理由,就GD的所谓简单的偏见为线性或其他“简单”的解决方案,特别是在训练中。在悲观方面,该论文表明这种结果是脆弱的。简单的数据操作可以使梯度流量会聚到具有次优裕度的线性分类器。
translated by 谷歌翻译
古典统计学习理论表示,拟合太多参数导致过度舒服和性能差。尽管大量参数矛盾,但是现代深度神经网络概括了这一发现,并构成了解释深度学习成功的主要未解决的问题。随机梯度下降(SGD)引起的隐式正规被认为是重要的,但其特定原则仍然是未知的。在这项工作中,我们研究了当地最小值周围的能量景观的局部几何学如何影响SGD的统计特性,具有高斯梯度噪声。我们争辩说,在合理的假设下,局部几何形状力强制SGD保持接近低维子空间,这会引起隐式正则化并导致深神经网络的泛化误差界定更严格的界限。为了获得神经网络的泛化误差界限,我们首先引入局部最小值周围的停滞迹象,并施加人口风险的局部基本凸性财产。在这些条件下,推导出SGD的下界,以保留在这些停滞套件中。如果发生停滞,我们会导出涉及权重矩阵的光谱规范的深神经网络的泛化误差的界限,但不是网络参数的数量。从技术上讲,我们的证据基于控制SGD中的参数值的变化以及基于局部最小值周围的合适邻域的熵迭代的参数值和局部均匀收敛。我们的工作试图通过统一收敛更好地连接非凸优化和泛化分析。
translated by 谷歌翻译
Neural networks with random weights appear in a variety of machine learning applications, most prominently as the initialization of many deep learning algorithms and as a computationally cheap alternative to fully learned neural networks. In the present article, we enhance the theoretical understanding of random neural networks by addressing the following data separation problem: under what conditions can a random neural network make two classes $\mathcal{X}^-, \mathcal{X}^+ \subset \mathbb{R}^d$ (with positive distance) linearly separable? We show that a sufficiently large two-layer ReLU-network with standard Gaussian weights and uniformly distributed biases can solve this problem with high probability. Crucially, the number of required neurons is explicitly linked to geometric properties of the underlying sets $\mathcal{X}^-, \mathcal{X}^+$ and their mutual arrangement. This instance-specific viewpoint allows us to overcome the usual curse of dimensionality (exponential width of the layers) in non-pathological situations where the data carries low-complexity structure. We quantify the relevant structure of the data in terms of a novel notion of mutual complexity (based on a localized version of Gaussian mean width), which leads to sound and informative separation guarantees. We connect our result with related lines of work on approximation, memorization, and generalization.
translated by 谷歌翻译
本文考虑了一个规范聚类问题,其中一个人从两个椭圆分布的平衡混合物中获取未标记的样本,并旨在估计标签的分类器。许多流行的方法包括PCA和K-Meanse需要混合物的各个组分在稍微球形,并且在拉伸时表现不佳。为了克服这个问题,我们提出了一个非凸面的程序寻求仿射变换,将数据转换为一维点云集中在$ -1 $和1美元之后,之后群集变得容易。我们的理论贡献是两倍:(1)我们表明,当样品大小超过维度的一些恒定倍数时,非凸损耗功能表现出理想的几何特性,以及(2)我们利用这一点,以证明这是一个有效的第一 - 订单算法在没有良好的初始化的情况下实现了近最佳统计精度。我们还提出了一般的方法,用于聚类,具有灵活的特征变换和损失目标。
translated by 谷歌翻译
训练神经网络的一种常见方法是将所有权重初始化为独立的高斯向量。我们观察到,通过将权重初始化为独立对,每对由两个相同的高斯向量组成,我们可以显着改善收敛分析。虽然已经研究了类似的技术来进行随机输入[Daniely,Neurips 2020],但尚未使用任意输入进行分析。使用此技术,我们展示了如何显着减少两层relu网络所需的神经元数量,均在逻辑损失的参数化设置不足的情况下,大约$ \ gamma^{ - 8} $ [Ji and telgarsky,ICLR, 2020]至$ \ gamma^{ - 2} $,其中$ \ gamma $表示带有神经切线内核的分离边距,以及在与平方损失的过度参数化设置中,从大约$ n^4 $ [song [song]和Yang,2019年]至$ n^2 $,隐含地改善了[Brand,Peng,Song和Weinstein,ITCS 2021]的近期运行时间。对于参数不足的设置,我们还证明了在先前工作时改善的新下限,并且在某些假设下是最好的。
translated by 谷歌翻译
我们介绍了嘈杂的特征混音(NFM),这是一个廉价但有效的数据增强方法,这些方法结合了基于插值的训练和噪声注入方案。不是用凸面的示例和它们的标签的凸面组合训练,而不是在输入和特征空间中使用对数据点对的噪声扰动凸组合。该方法包括混合和歧管混合作为特殊情况,但它具有额外的优点,包括更好地平滑决策边界并实现改进的模型鲁棒性。我们提供理论要理解这一点以及NFM的隐式正则化效果。与混合和歧管混合相比,我们的理论得到了经验结果的支持,展示了NFM的优势。我们表明,在一系列计算机视觉基准数据集中,使用NFM培训的剩余网络和视觉变压器在清洁数据的预测准确性和鲁棒性之间具有有利的权衡。
translated by 谷歌翻译
“良性过度装备”,分类器记住嘈杂的培训数据仍然达到良好的概括性表现,在机器学习界造成了很大的关注。为了解释这种令人惊讶的现象,一系列作品在过度参数化的线性回归,分类和内核方法中提供了理论典范。然而,如果在对逆势实例存在下仍发生良性的过度,则尚不清楚,即欺骗分类器的微小和有意的扰动的例子。在本文中,我们表明,良性过度确实发生在对抗性培训中,是防御对抗性实例的原则性的方法。详细地,我们证明了在$ \ ell_p $普发的扰动下的子高斯数据的混合中的普遍培训的线性分类器的风险限制。我们的结果表明,在中度扰动下,尽管过度禁止嘈杂的培训数据,所以发生前列训练的线性分类器可以实现近乎最佳的标准和对抗性风险。数值实验验证了我们的理论发现。
translated by 谷歌翻译
在负面的感知问题中,我们给出了$ n $数据点$({\ boldsymbol x} _i,y_i)$,其中$ {\ boldsymbol x} _i $是$ d $ -densional vector和$ y_i \ in \ { + 1,-1 \} $是二进制标签。数据不是线性可分离的,因此我们满足自己的内容,以找到最大的线性分类器,具有最大的\ emph {否定}余量。换句话说,我们想找到一个单位常规矢量$ {\ boldsymbol \ theta} $,最大化$ \ min_ {i \ le n} y_i \ langle {\ boldsymbol \ theta},{\ boldsymbol x} _i \ rangle $ 。这是一个非凸优化问题(它相当于在Polytope中找到最大标准矢量),我们在两个随机模型下研究其典型属性。我们考虑比例渐近,其中$ n,d \ to \ idty $以$ n / d \ to \ delta $,并在最大边缘$ \ kappa _ {\ text {s}}(\ delta)上证明了上限和下限)$或 - 等效 - 在其逆函数$ \ delta _ {\ text {s}}(\ kappa)$。换句话说,$ \ delta _ {\ text {s}}(\ kappa)$是overparametization阈值:以$ n / d \ le \ delta _ {\ text {s}}(\ kappa) - \ varepsilon $一个分类器实现了消失的训练错误,具有高概率,而以$ n / d \ ge \ delta _ {\ text {s}}(\ kappa)+ \ varepsilon $。我们在$ \ delta _ {\ text {s}}(\ kappa)$匹配,以$ \ kappa \ to - \ idty $匹配。然后,我们分析了线性编程算法来查找解决方案,并表征相应的阈值$ \ delta _ {\ text {lin}}(\ kappa)$。我们观察插值阈值$ \ delta _ {\ text {s}}(\ kappa)$和线性编程阈值$ \ delta _ {\ text {lin {lin}}(\ kappa)$之间的差距,提出了行为的问题其他算法。
translated by 谷歌翻译
The fundamental learning theory behind neural networks remains largely open. What classes of functions can neural networks actually learn? Why doesn't the trained network overfit when it is overparameterized?In this work, we prove that overparameterized neural networks can learn some notable concept classes, including two and three-layer networks with fewer parameters and smooth activations. Moreover, the learning can be simply done by SGD (stochastic gradient descent) or its variants in polynomial time using polynomially many samples. The sample complexity can also be almost independent of the number of parameters in the network.On the technique side, our analysis goes beyond the so-called NTK (neural tangent kernel) linearization of neural networks in prior works. We establish a new notion of quadratic approximation of the neural network (that can be viewed as a second-order variant of NTK), and connect it to the SGD theory of escaping saddle points.
translated by 谷歌翻译
Gradient descent finds a global minimum in training deep neural networks despite the objective function being non-convex. The current paper proves gradient descent achieves zero training loss in polynomial time for a deep overparameterized neural network with residual connections (ResNet). Our analysis relies on the particular structure of the Gram matrix induced by the neural network architecture. This structure allows us to show the Gram matrix is stable throughout the training process and this stability implies the global optimality of the gradient descent algorithm. We further extend our analysis to deep residual convolutional neural networks and obtain a similar convergence result.
translated by 谷歌翻译
Neural networks trained to minimize the logistic (a.k.a. cross-entropy) loss with gradient-based methods are observed to perform well in many supervised classification tasks. Towards understanding this phenomenon, we analyze the training and generalization behavior of infinitely wide two-layer neural networks with homogeneous activations. We show that the limits of the gradient flow on exponentially tailed losses can be fully characterized as a max-margin classifier in a certain non-Hilbertian space of functions. In presence of hidden low-dimensional structures, the resulting margin is independent of the ambiant dimension, which leads to strong generalization bounds. In contrast, training only the output layer implicitly solves a kernel support vector machine, which a priori does not enjoy such an adaptivity. Our analysis of training is non-quantitative in terms of running time but we prove computational guarantees in simplified settings by showing equivalences with online mirror descent. Finally, numerical experiments suggest that our analysis describes well the practical behavior of two-layer neural networks with ReLU activations and confirm the statistical benefits of this implicit bias.
translated by 谷歌翻译