过度参数化神经网络（NN）的损失表面具有许多全球最小值，却零训练误差。我们解释了标准NN训练程序的常见变体如何改变获得的最小化器。首先，我们明确说明了强烈参数化的NN初始化的大小如何影响最小化器，并可能恶化其最终的测试性能。我们提出了限制这种效果的策略。然后，我们证明，对于自适应优化（例如Adagrad），所获得的最小化器通常与梯度下降（GD）最小化器不同。随机迷你批次训练，即使在非自适应情况下，GD和随机GD基本相同的最小化器，这种自适应最小化器也会进一步改变。最后，我们解释说，这些效果仍然与较少参数化的NN相关。尽管过度参数具有其好处，但我们的工作强调，它会导致参数化模型缺乏错误来源。

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。

现代神经网络通常以强烈的过度构造状态运行：它们包含许多参数，即使实际标签被纯粹随机的标签代替，它们也可以插入训练集。尽管如此，他们在看不见的数据上达到了良好的预测错误：插值训练集并不会导致巨大的概括错误。此外，过度散色化似乎是有益的，因为它简化了优化景观。在这里，我们在神经切线（NT）制度中的两层神经网络的背景下研究这些现象。我们考虑了一个简单的数据模型，以及各向同性协变量的矢量，$ d $尺寸和$ n $隐藏的神经元。我们假设样本量$ n $和尺寸$ d $都很大，并且它们在多项式上相关。我们的第一个主要结果是对过份术的经验NT内核的特征结构的特征。这种表征意味着必然的表明，经验NT内核的最低特征值在$ ND \ gg n $后立即从零界限，因此网络可以在同一制度中精确插值任意标签。我们的第二个主要结果是对NT Ridge回归的概括误差的表征，包括特殊情况，最小值-ULL_2 $ NORD插值。我们证明，一旦$ nd \ gg n $，测试误差就会被内核岭回归之一相对于无限宽度内核而近似。多项式脊回归的误差依次近似后者，从而通过与激活函数的高度组件相关的“自我诱导的”项增加了正则化参数。多项式程度取决于样本量和尺寸（尤其是$ \ log n/\ log d $）。

过分分度化是没有凸起的关键因素，以解释神经网络的全局渐变（GD）的全局融合。除了研究良好的懒惰政权旁边，已经为浅网络开发了无限宽度（平均场）分析，使用凸优化技术。为了弥合懒惰和平均场制度之间的差距，我们研究残留的网络（RESNET），其中残留块具有线性参数化，同时仍然是非线性的。这种Resnets承认无限深度和宽度限制，在再现内核Hilbert空间（RKHS）中编码残差块。在这个限制中，我们证明了当地的Polyak-Lojasiewicz不等式。因此，每个关键点都是全球最小化器和GD的局部收敛结果，并检索懒惰的制度。与其他平均场研究相比，它在残留物的表达条件下适用于参数和非参数案。我们的分析导致实用和量化的配方：从通用RKHS开始，应用随机傅里叶特征来获得满足我们的表征条件的高概率的有限维参数化。

A longstanding goal in deep learning research has been to precisely characterize training and generalization. However, the often complex loss landscapes of neural networks have made a theory of learning dynamics elusive. In this work, we show that for wide neural networks the learning dynamics simplify considerably and that, in the infinite width limit, they are governed by a linear model obtained from the first-order Taylor expansion of the network around its initial parameters. Furthermore, mirroring the correspondence between wide Bayesian neural networks and Gaussian processes, gradient-based training of wide neural networks with a squared loss produces test set predictions drawn from a Gaussian process with a particular compositional kernel. While these theoretical results are only exact in the infinite width limit, we nevertheless find excellent empirical agreement between the predictions of the original network and those of the linearized version even for finite practically-sized networks. This agreement is robust across different architectures, optimization methods, and loss functions.

Autoencoders are a popular model in many branches of machine learning and lossy data compression. However, their fundamental limits, the performance of gradient methods and the features learnt during optimization remain poorly understood, even in the two-layer setting. In fact, earlier work has considered either linear autoencoders or specific training regimes (leading to vanishing or diverging compression rates). Our paper addresses this gap by focusing on non-linear two-layer autoencoders trained in the challenging proportional regime in which the input dimension scales linearly with the size of the representation. Our results characterize the minimizers of the population risk, and show that such minimizers are achieved by gradient methods; their structure is also unveiled, thus leading to a concise description of the features obtained via training. For the special case of a sign activation function, our analysis establishes the fundamental limits for the lossy compression of Gaussian sources via (shallow) autoencoders. Finally, while the results are proved for Gaussian data, numerical simulations on standard datasets display the universality of the theoretical predictions.

清晰度感知最小化（SAM）是一种最近的训练方法，它依赖于最严重的重量扰动，可显着改善各种环境中的概括。我们认为，基于pac-bayes概括结合的SAM成功的现有理由，而收敛到平面最小值的想法是不完整的。此外，没有解释说在SAM中使用$ m $ sharpness的成功，这对于概括而言至关重要。为了更好地理解SAM的这一方面，我们理论上分析了其对角线性网络的隐式偏差。我们证明，SAM总是选择一种比标准梯度下降更好的解决方案，用于某些类别的问题，并且通过使用$ m $ -sharpness可以放大这种效果。我们进一步研究了隐性偏见在非线性网络上的特性，在经验上，我们表明使用SAM进行微调的标准模型可以导致显着的概括改进。最后，当与随机梯度一起使用时，我们为非凸目标提供了SAM的收敛结果。我们从经验上说明了深层网络的这些结果，并讨论了它们与SAM的概括行为的关系。我们的实验代码可在https://github.com/tml-epfl/understanding-sam上获得。

当我们扩大数据集，模型尺寸和培训时间时，深入学习方法的能力中存在越来越多的经验证据。尽管有一些关于这些资源如何调节统计能力的说法，但对它们对模型培训的计算问题的影响知之甚少。这项工作通过学习$ k $ -sparse $ n $ bits的镜头进行了探索，这是一个构成理论计算障碍的规范性问题。在这种情况下，我们发现神经网络在扩大数据集大小和运行时间时会表现出令人惊讶的相变。特别是，我们从经验上证明，通过标准培训，各种体系结构以$ n^{o（k）} $示例学习稀疏的平等，而损失（和错误）曲线在$ n^{o（k）}后突然下降。 $迭代。这些积极的结果几乎匹配已知的SQ下限，即使没有明确的稀疏性先验。我们通过理论分析阐明了这些现象的机制：我们发现性能的相变不到SGD“在黑暗中绊倒”，直到它找到了隐藏的特征集（自然算法也以$ n^中的方式运行{o（k）} $ time）;取而代之的是，我们表明SGD逐渐扩大了人口梯度的傅立叶差距。

A recent line of work studies overparametrized neural networks in the "kernel regime," i.e. when the network behaves during training as a kernelized linear predictor, and thus training with gradient descent has the effect of finding the minimum RKHS norm solution. This stands in contrast to other studies which demonstrate how gradient descent on overparametrized multilayer networks can induce rich implicit biases that are not RKHS norms. Building on an observation by Chizat and Bach [2018], we show how the scale of the initialization controls the transition between the "kernel" (aka lazy) and "rich" (aka active) regimes and affects generalization properties in multilayer homogeneous models. We provide a complete and detailed analysis for a simple two-layer model that already exhibits an interesting and meaningful transition between the kernel and rich regimes, and we demonstrate the transition for more complex matrix factorization models and multilayer non-linear networks.

Deep neural networks (DNNs) have demonstrated dominating performance in many fields; since AlexNet, networks used in practice are going wider and deeper. On the theoretical side, a long line of works have been focusing on why we can train neural networks when there is only one hidden layer. The theory of multi-layer networks remains unsettled. In this work, we prove simple algorithms such as stochastic gradient descent (SGD) can find global minima on the training objective of DNNs in polynomial time. We only make two assumptions: the inputs do not degenerate and the network is over-parameterized. The latter means the number of hidden neurons is sufficiently large: polynomial in L, the number of DNN layers and in n, the number of training samples. As concrete examples, starting from randomly initialized weights, we show that SGD attains 100% training accuracy in classification tasks, or minimizes regression loss in linear convergence speed ε ∝ e −Ω(T ) , with running time polynomial in n and L. Our theory applies to the widely-used but non-smooth ReLU activation, and to any smooth and possibly non-convex loss functions. In terms of network architectures, our theory at least applies to fully-connected neural networks, convolutional neural networks (CNN), and residual neural networks (ResNet).* Equal contribution . Full version and future updates are available at https://arxiv.org/abs/1811.03962.This paper is a follow up to the recurrent neural network (RNN) paper (Allen-Zhu et al., 2018b) by the same set of authors. Most of the techniques used in this paper were already discovered in the RNN paper, and this paper can be viewed as a simplification (or to some extent a special case) of the RNN setting in order to reach out to a wider audience. We compare the difference and mention our additional contribution in Section 1.2.

微调是深度学习的常见做法，使用相对较少的训练数据来实现卓越的普遍性导致下游任务。虽然在实践中广泛使用，但它缺乏强烈的理论理解。我们分析了若干架构中线性教师的回归的本方案的样本复杂性。直观地，微调的成功取决于源任务与目标任务之间的相似性，但是测量它是非微不足道的。我们表明相关措施考虑了源任务，目标任务和目标数据的协方差结构之间的关系。在线性回归的设置中，我们表明，在现实的情况下，当上述措施低时，在实际设置下，显着的样本复杂性降低是合理的。对于深线性回归，我们在用预制权重初始化网络时，我们提出了关于基于梯度训练的感应偏差的新颖结果。使用此结果，我们显示此设置的相似度量也受网络深度的影响。我们进一步在浅relu模型上显示结果，并分析了在源和目标任务中的样本复杂性的依赖性。我们经验证明了我们对合成和现实数据的结果。

In a series of recent theoretical works, it was shown that strongly overparameterized neural networks trained with gradient-based methods could converge exponentially fast to zero training loss, with their parameters hardly varying. In this work, we show that this "lazy training" phenomenon is not specific to overparameterized neural networks, and is due to a choice of scaling, often implicit, that makes the model behave as its linearization around the initialization, thus yielding a model equivalent to learning with positive-definite kernels. Through a theoretical analysis, we exhibit various situations where this phenomenon arises in non-convex optimization and we provide bounds on the distance between the lazy and linearized optimization paths. Our numerical experiments bring a critical note, as we observe that the performance of commonly used non-linear deep convolutional neural networks in computer vision degrades when trained in the lazy regime. This makes it unlikely that "lazy training" is behind the many successes of neural networks in difficult high dimensional tasks.

了解培训算法的隐含偏差至关重要，以解释过度分化的神经网络的成功。在本文中，我们通过连续时间版本，即随机梯度流来研究对对角线线性网络的随机梯度下降的动态。我们明确地表征了随机流动选择的解决方案，并证明它总是享有比梯度流量更好的泛化特性。令人惊讶的是，我们表明训练损失的收敛速度控制了偏置效果的大小：收敛速度较慢，偏置越好。要完全完成我们的分析，我们提供动态的收敛保证。我们还提供了支持我们的理论索赔的实验结果。我们的研究结果强调了结构化噪音可以引起更好的概括，并且它们有助于解释在梯度下降的随机梯度下降方面观察到的更大表现。

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.

具有动量的迷你批次SGD是学习大型预测模型的基本算法。在本文中，我们开发了一个新的分析框架，以分析不同动量和批次大小的线性模型的迷你批次SGD。我们的关键思想是用其生成函数来描述损耗值序列，可以以紧凑的形式写出，假设模型权重的第二矩对角近似。通过分析这种生成功能，我们得出了有关收敛条件，模型相结构和最佳学习设置的各种结论。作为几个示例，我们表明1）优化轨迹通常可以从“信号主导”转换为“噪声主导”阶段，以分析性预测的时间尺度； 2）在“信号主导”（但不是“以噪声为主导”的）阶段中，有利于选择较大的有效学习率，但是对于任何有限的批次大小，其值必须受到限制，以避免发散； 3）可以在负动量下实现最佳收敛速率。我们通过对MNIST和合成问题进行广泛的实验来验证我们的理论预测，并找到良好的定量一致性。

对于由缺陷线性回归中的标签噪声引起的预期平均平方概率，我们证明了无渐近分布的下限。我们的下部结合概括了过度公共数据（内插）制度的类似已知结果。与最先前的作品相比，我们的分析适用于广泛的输入分布，几乎肯定的全排列功能矩阵，允许我们涵盖各种类型的确定性或随机特征映射。我们的下限是渐近的锐利，暗示在存在标签噪声时，缺陷的线性回归不会在任何这些特征映射中围绕内插阈值进行良好的。我们详细分析了强加的假设，并为分析（随机）特征映射提供了理论。使用此理论，我们可以表明我们的假设对于具有（Lebesgue）密度的输入分布以及随机深神经网络给出的特征映射，具有Sigmoid，Tanh，SoftPlus或Gelu等分析激活功能。作为进一步的例子，我们示出了来自随机傅里叶特征和多项式内核的特征映射也满足我们的假设。通过进一步的实验和分析结果，我们补充了我们的理论。

This paper studies the infinite-width limit of deep linear neural networks initialized with random parameters. We obtain that, when the number of neurons diverges, the training dynamics converge (in a precise sense) to the dynamics obtained from a gradient descent on an infinitely wide deterministic linear neural network. Moreover, even if the weights remain random, we get their precise law along the training dynamics, and prove a quantitative convergence result of the linear predictor in terms of the number of neurons. We finally study the continuous-time limit obtained for infinitely wide linear neural networks and show that the linear predictors of the neural network converge at an exponential rate to the minimal $\ell_2$-norm minimizer of the risk.

最近的研究表明，通过梯度下降训练的无限宽神经网络（NN）的动态可以是神经切线核（NTK）\ CITEP {Jacot2018neural}的特征。在平方损失下，通过梯度下降训练的无限宽度NN，具有无限小的学习速率等同于与NTK \ CITEP {arora2019Exact}的内核回归。但是，当前ridge回归{arora2019Harnessing}只知道等价物，而NN和其他内核机（KMS）之间的等价，例如，支持向量机（SVM），仍然未知。因此，在这项工作中，我们建议在NN和SVM之间建立等效，具体而言，通过柔软的边缘损失和具有由子润发性培训的NTK培训的标准柔软裕度SVM培训的无限宽NN。我们的主要理论结果包括建立NN和广泛的$ \ ELL_2 $正规化KMS之间的等价，其中有限宽度界限，不能通过事先工作来处理，并显示出通过这种正规化损耗函数训练的每个有限宽度NN大约一公里。此外，我们展示了我们的理论可以实现三种实际应用，包括（i）\ yressit {非空心}通过相应的km界限Nn; （ii）无限宽度NN的\ yryit {非琐碎}鲁棒性证书（而现有的鲁棒性验证方法提供空中界定）; （iii）本质上更强大的无限宽度NN，来自以前的内核回归。我们的实验代码可用于\ URL {https://github.com/leslie-ch/equiv-nn-svm}。

Artificial neural networks are functions depending on a finite number of parameters typically encoded as weights and biases. The identification of the parameters of the network from finite samples of input-output pairs is often referred to as the \emph{teacher-student model}, and this model has represented a popular framework for understanding training and generalization. Even if the problem is NP-complete in the worst case, a rapidly growing literature -- after adding suitable distributional assumptions -- has established finite sample identification of two-layer networks with a number of neurons $m=\mathcal O(D)$, $D$ being the input dimension. For the range $D<m<D^2$ the problem becomes harder, and truly little is known for networks parametrized by biases as well. This paper fills the gap by providing constructive methods and theoretical guarantees of finite sample identification for such wider shallow networks with biases. Our approach is based on a two-step pipeline: first, we recover the direction of the weights, by exploiting second order information; next, we identify the signs by suitable algebraic evaluations, and we recover the biases by empirical risk minimization via gradient descent. Numerical results demonstrate the effectiveness of our approach.

在许多情况下，更简单的模型比更复杂的模型更可取，并且该模型复杂性的控制是机器学习中许多方法的目标，例如正则化，高参数调整和体系结构设计。在深度学习中，很难理解复杂性控制的潜在机制，因为许多传统措施并不适合深度神经网络。在这里，我们开发了几何复杂性的概念，该概念是使用离散的dirichlet能量计算的模型函数变异性的量度。使用理论论据和经验结果的结合，我们表明，许多常见的训练启发式方法，例如参数规范正规化，光谱规范正则化，平稳性正则化，隐式梯度正则化，噪声正则化和参数初始化的选择，都可以控制几何学复杂性，并提供一个统一的框架，以表征深度学习模型的行为。