权重规范$ \ | w \ | $和保证金$ \ gamma $通过归一化的保证金$ \ gamma/\ | w \ | $参与学习理论。由于标准神经净优化器不能控制归一化的边缘，因此很难测试该数量是否与概括有关。本文设计了一系列实验研究，这些研究明确控制了归一化的边缘，从而解决了两个核心问题。首先：归一化的边缘是否总是对概括产生因果影响？本文发现，在归一化的边缘似乎与概括没有关系的情况下，可以与Bartlett等人的理论背道而驰。（2017）。第二：标准化边缘是否对概括有因果影响？该论文发现是的 - 在标准培训设置中，测试性能紧密跟踪了标准化的边距。该论文将高斯流程模型表示为这种行为的有前途的解释。

With a goal of understanding what drives generalization in deep networks, we consider several recently suggested explanations, including norm-based control, sharpness and robustness. We study how these measures can ensure generalization, highlighting the importance of scale normalization, and making a connection between sharpness and PAC-Bayes theory. We then investigate how well the measures explain different observed phenomena.

缺乏对深度学习系统的洞察力阻碍了他们的系统设计。在科学和工程学中，建模是一种用于了解内部过程不透明的复杂系统的方法。建模用更简单的代理代替复杂的系统，该系统更适合解释。从中汲取灵感，我们使用高斯流程为神经网络构建了一类代理模型。我们没有从神经网络的某些限制案例中得出内核，而是从经验上从神经网络的自然主义行为中学习了高斯过程的内核。我们首先通过两项案例研究评估我们的方法，灵感来自先前对神经网络行为的理论研究，在这些案例研究中，我们捕获了学习低频的神经网络偏好，并确定了深层神经网络中的病理行为。在进一步的实践案例研究中，我们使用学识渊博的内核来预测神经网络的泛化特性。

It has long been known that a single-layer fully-connected neural network with an i.i.d. prior over its parameters is equivalent to a Gaussian process (GP), in the limit of infinite network width. This correspondence enables exact Bayesian inference for infinite width neural networks on regression tasks by means of evaluating the corresponding GP. Recently, kernel functions which mimic multi-layer random neural networks have been developed, but only outside of a Bayesian framework. As such, previous work has not identified that these kernels can be used as covariance functions for GPs and allow fully Bayesian prediction with a deep neural network. In this work, we derive the exact equivalence between infinitely wide deep networks and GPs. We further develop a computationally efficient pipeline to compute the covariance function for these GPs. We then use the resulting GPs to perform Bayesian inference for wide deep neural networks on MNIST and CIFAR-10. We observe that trained neural network accuracy approaches that of the corresponding GP with increasing layer width, and that the GP uncertainty is strongly correlated with trained network prediction error. We further find that test performance increases as finite-width trained networks are made wider and more similar to a GP, and thus that GP predictions typically outperform those of finite-width networks. Finally we connect the performance of these GPs to the recent theory of signal propagation in random neural networks. * Both authors contributed equally to this work. † Work done as a member of the Google AI Residency program (g.co/airesidency). 1 Throughout this paper, we assume the conditions on the parameter distributions and nonlinearities are such that the Central Limit Theorem will hold; for instance, that the weight variance is scaled inversely proportional to the layer width.

估计深神经网络（DNN）的概括误差（GE）是一项重要任务，通常依赖于持有数据的可用性。基于单个训练集更好地预测GE的能力可能会产生总体DNN设计原则，以减少对试用和错误的依赖以及其他绩效评估优势。为了寻找与GE相关的数量，我们使用无限宽度DNN限制到绑定的MI，研究了输入和最终层表示之间的相互信息（MI）。现有的基于输入压缩的GE绑定用于链接MI和GE。据我们所知，这代表了该界限的首次实证研究。为了实证伪造理论界限，我们发现它通常对于表现最佳模型而言通常很紧。此外，它在许多情况下检测到训练标签的随机化，反映了测试时间扰动的鲁棒性，并且只有很少的培训样本就可以很好地工作。考虑到输入压缩是广泛适用的，可以在信心估算MI的情况下，这些结果是有希望的。

为了更好地了解大型神经网络的理论行为，有几项工程已经分析了网络宽度倾向于无穷大的情况。在该制度中，随机初始化的影响和训练神经网络的过程可以与高斯过程和神经切线内核等分析工具正式表达。在本文中，我们审查了在这种无限宽度神经网络中量化不确定性的方法，并将它们与贝叶斯推理框架中的高斯过程的关系进行比较。我们利用沿途使用几个等价结果，以获得预测不确定性的确切闭合性解决方案。

大型多层神经网络的概括性能越来越兴趣，可以接受训练以达到零训练错误，同时对测试数据进行良好的推广。该制度被称为“第二次下降”，似乎与常规观点相矛盾，即最佳模型复杂性应反映出不足和过度拟合之间的最佳平衡，即偏见差异权衡。本文介绍了双重下降的VC理论分析，并表明可以通过经典的VC将军范围来充分解释。我们说明了分析性VC结合的应用，用于对分类问题进行两次下降进行建模，并使用多种学习方法（例如SVM，最小二乘正方形和多层观察者分类器）的经验结果。此外，我们讨论了对深度学习社区中VC理论结果误解的几个原因。

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.

Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small difference between training and test performance. Conventional wisdom attributes small generalization error either to properties of the model family, or to the regularization techniques used during training. Through extensive systematic experiments, we show how these traditional approaches fail to explain why large neural networks generalize well in practice. Specifically, our experiments establish that state-of-the-art convolutional networks for image classification trained with stochastic gradient methods easily fit a random labeling of the training data. This phenomenon is qualitatively unaffected by explicit regularization, and occurs even if we replace the true images by completely unstructured random noise. We corroborate these experimental findings with a theoretical construction showing that simple depth two neural networks already have perfect finite sample expressivity as soon as the number of parameters exceeds the number of data points as it usually does in practice. We interpret our experimental findings by comparison with traditional models. * Work performed while interning at Google Brain.† Work performed at Google Brain.

神经切线核是根据无限宽度神经网络的参数分布定义的内核函数。尽管该极限不切实际，但神经切线内核允许对神经网络进行更直接的研究，并凝视着黑匣子的面纱。最近，从理论上讲，Laplace内核和神经切线内核在$ \ Mathbb {S}}^{D-1} $中共享相同的复制核Hilbert空间，暗示了它们的等价。在这项工作中，我们分析了两个内核的实际等效性。我们首先是通过与核的准确匹配，然后通过与高斯过程的后代匹配来进行匹配。此外，我们分析了$ \ mathbb {r}^d $中的内核，并在回归任务中进行实验。

Learning curves provide insight into the dependence of a learner's generalization performance on the training set size. This important tool can be used for model selection, to predict the effect of more training data, and to reduce the computational complexity of model training and hyperparameter tuning. This review recounts the origins of the term, provides a formal definition of the learning curve, and briefly covers basics such as its estimation. Our main contribution is a comprehensive overview of the literature regarding the shape of learning curves. We discuss empirical and theoretical evidence that supports well-behaved curves that often have the shape of a power law or an exponential. We consider the learning curves of Gaussian processes, the complex shapes they can display, and the factors influencing them. We draw specific attention to examples of learning curves that are ill-behaved, showing worse learning performance with more training data. To wrap up, we point out various open problems that warrant deeper empirical and theoretical investigation. All in all, our review underscores that learning curves are surprisingly diverse and no universal model can be identified.

Accurate uncertainty quantification is a major challenge in deep learning, as neural networks can make overconfident errors and assign high confidence predictions to out-of-distribution (OOD) inputs. The most popular approaches to estimate predictive uncertainty in deep learning are methods that combine predictions from multiple neural networks, such as Bayesian neural networks (BNNs) and deep ensembles. However their practicality in real-time, industrial-scale applications are limited due to the high memory and computational cost. Furthermore, ensembles and BNNs do not necessarily fix all the issues with the underlying member networks. In this work, we study principled approaches to improve uncertainty property of a single network, based on a single, deterministic representation. By formalizing the uncertainty quantification as a minimax learning problem, we first identify distance awareness, i.e., the model's ability to quantify the distance of a testing example from the training data, as a necessary condition for a DNN to achieve high-quality (i.e., minimax optimal) uncertainty estimation. We then propose Spectral-normalized Neural Gaussian Process (SNGP), a simple method that improves the distance-awareness ability of modern DNNs with two simple changes: (1) applying spectral normalization to hidden weights to enforce bi-Lipschitz smoothness in representations and (2) replacing the last output layer with a Gaussian process layer. On a suite of vision and language understanding benchmarks, SNGP outperforms other single-model approaches in prediction, calibration and out-of-domain detection. Furthermore, SNGP provides complementary benefits to popular techniques such as deep ensembles and data augmentation, making it a simple and scalable building block for probabilistic deep learning. Code is open-sourced at https://github.com/google/uncertainty-baselines

我们通过将其基于实现功能空间而不是参数空间的几何形状来系统地研究深度神经网络景观的方法。将分类器分组到等效类中，我们开发了一个标准化的参数化，其中所有对称性都被删除，从而导致环形拓扑。在这个空间上，我们探讨了误差景观而不是损失。这使我们能够得出有意义的概念，即最小化器的平坦度和连接它们的地球通道的概念。使用不同的优化算法，这些算法采样具有不同平坦度的最小化器，我们研究模式连接性和相对距离。测试各种最先进的体系结构和基准数据集，我们确认了平面度和泛化性能之间的相关性；我们进一步表明，在功能空间中，minima彼此更近，并且连接它们的大地测量学的屏障很小。我们还发现，通过梯度下降的变体发现的最小化器可以通过由参数空间中的两个直线组成的零误差路径连接，即带有单个弯曲的多边形链。我们观察到具有二进制权重和激活的神经网络中相似的定性结果，这为在这种情况下的连通性提供了第一个结果之一。我们的结果取决于对称性的去除，并且与对简单浅层模型进行的一些分析研究所描述的丰富现象学非常吻合。

我们研究了回归中神经网络（NNS）的模型不确定性的方法。为了隔离模型不确定性的效果，我们专注于稀缺训练数据的无噪声环境。我们介绍了关于任何方法都应满足的模型不确定性的五个重要的逃亡者。但是，我们发现，建立的基准通常无法可靠地捕获其中一些逃避者，即使是贝叶斯理论要求的基准。为了解决这个问题，我们介绍了一种新方法来捕获NNS的模型不确定性，我们称之为基于神经优化的模型不确定性（NOMU）。 NOMU的主要思想是设计一个由两个连接的子NN组成的网络体系结构，一个用于模型预测，一个用于模型不确定性，并使用精心设计的损耗函数进行训练。重要的是，我们的设计执行NOMU满足我们的五个Desiderata。由于其模块化体系结构，NOMU可以为任何给定（先前训练）NN提供模型不确定性，如果访问其培训数据。我们在各种回归任务和无嘈杂的贝叶斯优化（BO）中评估NOMU，并具有昂贵的评估。在回归中，NOMU至少和最先进的方法。在BO中，Nomu甚至胜过所有考虑的基准。

This paper presents a margin-based multiclass generalization bound for neural networks that scales with their margin-normalized spectral complexity: their Lipschitz constant, meaning the product of the spectral norms of the weight matrices, times a certain correction factor. This bound is empirically investigated for a standard AlexNet network trained with SGD on the mnist and cifar10 datasets, with both original and random labels; the bound, the Lipschitz constants, and the excess risks are all in direct correlation, suggesting both that SGD selects predictors whose complexity scales with the difficulty of the learning task, and secondly that the presented bound is sensitive to this complexity.

对对抗攻击的脆弱性是在安全至关重要应用中采用深度学习的主要障碍之一。尽管做出了巨大的努力，但无论是实用还是理论上的，培训深度学习模型对对抗性攻击仍然是一个悬而未决的问题。在本文中，我们分析了大数据，贝叶斯神经网络（BNNS）中的对抗性攻击的几何形状。我们表明，在限制下，由于数据分布的堕落而产生了基于梯度的攻击的脆弱性，即当数据位于环境空间的较低维度的亚策略上时。直接结果，我们证明，在此限制下，BNN后代对基于梯度的对抗性攻击是强大的。至关重要的是，我们证明，即使从后部采样的每个神经网络都很容易受到基于梯度的攻击，因此相对于BNN后验分布的预期损失梯度正在消失。 MNIST，时尚MNIST和半卫星数据集的实验结果，代表有限的数据制度，并接受了汉密尔顿蒙特卡洛和变异推理的BNN，支持这一论点，表明BNN可以在清洁数据和稳健性上表现出很高的精度对基于梯度和无梯度的对抗性攻击。

我们专注于具有单个隐藏层的特定浅神经网络，即具有$ l_2 $ normalistization的数据以及Sigmoid形状的高斯错误函数（“ ERF”）激活或高斯错误线性单元（GELU）激活。对于这些网络，我们通过Pac-Bayesian理论得出了新的泛化界限。与大多数现有的界限不同，它们适用于具有确定性或随机参数的神经网络。当网络接受Mnist和Fashion-Mnist上的香草随机梯度下降训练时，我们的界限在经验上是无效的。

尽管过度参数过多，但人们认为，通过随机梯度下降（SGD）训练的深度神经网络令人惊讶地概括了。基于预先指定的假设集的Rademacher复杂性，已经开发出不同的基于规范的泛化界限来解释这种现象。但是，最近的研究表明，这些界限可能会随着训练集的规模而增加，这与经验证据相反。在这项研究中，我们认为假设集SGD探索是轨迹依赖性的，因此可能在其Rademacher复杂性上提供更严格的结合。为此，我们通过假设发生的随机梯度噪声遵循分数的布朗运动，通过随机微分方程来表征SGD递归。然后，我们根据覆盖数字识别Rademacher的复杂性，并将其与优化轨迹的Hausdorff维度相关联。通过调用假设集稳定性，我们得出了针对深神经网络的新型概括。广泛的实验表明，它可以很好地预测几种常见的实验干预措施的概括差距。我们进一步表明，分数布朗运动的HURST参数比现有的概括指标（例如幂律指数和上blumenthal-getoor索引）更具信息性。

鉴于对机器学习模型的访问，可以进行对手重建模型的培训数据？这项工作从一个强大的知情对手的镜头研究了这个问题，他们知道除了一个之外的所有培训数据点。通过实例化混凝土攻击，我们表明重建此严格威胁模型中的剩余数据点是可行的。对于凸模型（例如Logistic回归），重建攻击很简单，可以以封闭形式导出。对于更常规的模型（例如神经网络），我们提出了一种基于训练的攻击策略，该攻击策略接收作为输入攻击的模型的权重，并产生目标数据点。我们展示了我们对MNIST和CIFAR-10训练的图像分类器的攻击的有效性，并系统地研究了标准机器学习管道的哪些因素影响重建成功。最后，我们从理论上调查了有多差异的隐私足以通过知情对手减轻重建攻击。我们的工作提供了有效的重建攻击，模型开发人员可以用于评估超出以前作品中考虑的一般设置中的个别点的记忆（例如，生成语言模型或访问培训梯度）;它表明，标准模型具有存储足够信息的能力，以实现培训数据点的高保真重建;它表明，差异隐私可以成功减轻该参数制度中的攻击，其中公用事业劣化最小。

在最近的几项研究中已经显示了过度参数化在实现卓越概括性能方面的好处，证明了在实践中使用较大模型的趋势。然而，在强大的学习背景下，神经网络大小的影响尚未得到很好的研究。在这项工作中，我们发现，在大量错误标记的示例的存在下，将网络大小的增加超出某个点可能是有害的。特别是，当标签噪声增加时，最初是单调或“双重下降”测试损失曲线（W.R.T.网络宽度）变成U形或双U形曲线，这表明某些模型具有中等大小的模型实现了最佳的概括。我们观察到，当通过随机修剪通过密度控制网络大小时，观察到相似的测试损失行为。我们还通过偏置变化分解和理论上表征标签噪声塑造方差项的方式来仔细研究现象。即使采用最新的鲁棒方法，也可以观察到测试损失的类似行为，这表明限制网络大小可以进一步提高现有方法。最后，我们从经验上检查网络大小对学习函数平稳性的影响，并发现最初的大小和平滑度之间的负相关性是由标签噪声翻转的。