Neural sequence models, especially transformers, exhibit a remarkable capacity for in-context learning. They can construct new predictors from sequences of labeled examples $(x, f(x))$ presented in the input without further parameter updates. We investigate the hypothesis that transformer-based in-context learners implement standard learning algorithms implicitly, by encoding smaller models in their activations, and updating these implicit models as new examples appear in the context. Using linear regression as a prototypical problem, we offer three sources of evidence for this hypothesis. First, we prove by construction that transformers can implement learning algorithms for linear models based on gradient descent and closed-form ridge regression. Second, we show that trained in-context learners closely match the predictors computed by gradient descent, ridge regression, and exact least-squares regression, transitioning between different predictors as transformer depth and dataset noise vary, and converging to Bayesian estimators for large widths and depths. Third, we present preliminary evidence that in-context learners share algorithmic features with these predictors: learners' late layers non-linearly encode weight vectors and moment matrices. These results suggest that in-context learning is understandable in algorithmic terms, and that (at least in the linear case) learners may rediscover standard estimation algorithms. Code and reference implementations are released at https://github.com/ekinakyurek/google-research/blob/master/incontext.

Transformers have become the state-of-the-art neural network architecture across numerous domains of machine learning. This is partly due to their celebrated ability to transfer and to learn in-context based on few examples. Nevertheless, the mechanisms by which Transformers become in-context learners are not well understood and remain mostly an intuition. Here, we argue that training Transformers on auto-regressive tasks can be closely related to well-known gradient-based meta-learning formulations. We start by providing a simple weight construction that shows the equivalence of data transformations induced by 1) a single linear self-attention layer and by 2) gradient-descent (GD) on a regression loss. Motivated by that construction, we show empirically that when training self-attention-only Transformers on simple regression tasks either the models learned by GD and Transformers show great similarity or, remarkably, the weights found by optimization match the construction. Thus we show how trained Transformers implement gradient descent in their forward pass. This allows us, at least in the domain of regression problems, to mechanistically understand the inner workings of optimized Transformers that learn in-context. Furthermore, we identify how Transformers surpass plain gradient descent by an iterative curvature correction and learn linear models on deep data representations to solve non-linear regression tasks. Finally, we discuss intriguing parallels to a mechanism identified to be crucial for in-context learning termed induction-head (Olsson et al., 2022) and show how it could be understood as a specific case of in-context learning by gradient descent learning within Transformers.

中文学习是指模型在及时序列中条件条件的能力，该序列由内部下文示例（输入输出对，与某些任务相对应）以及新的查询输入，并生成相应的输出。至关重要的是，内在学习仅在推理时间发生，而没有任何参数更新模型。尽管大型语言模型（例如GPT-3）具有某种能力来执行中文学习的能力，但尚不清楚任务成功的任务之间的关系以及培训数据中存在的内容。为了取得进步朝着理解文本学习的进步，我们考虑了训练模型的明确定义的问题，以学习函数类（例如，线性函数）：也就是说，给定的数据从类中的某些功能衍生而成，可以我们训练一个模型以在此课程中学习“大多数”功能？我们从经验上表明，可以从头开始训练标准变压器，以执行线性函数的文本学习 - 也就是说，训练有素的模型能够从具有与最佳最小二乘估计器相当的性能的示例中学习看不见的线性函数。实际上，即使在两种形式的分配变化下，也可能进行中文学习：（i）模型的训练数据和推理时间提示之间，以及（ii）在推理过程中的内在示例和查询输入之间。我们还表明，我们可以训练变形金刚在文本中学习更多复杂的功能类，即稀疏线性功能，两层神经网络和决策树 - 具有匹配或超过特定于任务特定的学习算法的性能。我们的代码和模型可在https://github.com/dtsip/in-context-learning上找到。

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。

这项正在进行的工作旨在为统计学习提供统一的介绍，从诸如GMM和HMM等经典模型到现代神经网络（如VAE和扩散模型）缓慢地构建。如今，有许多互联网资源可以孤立地解释这一点或新的机器学习算法，但是它们并没有（也不能在如此简短的空间中）将这些算法彼此连接起来，或者与统计模型的经典文献相连现代算法出现了。同样明显缺乏的是一个单一的符号系统，尽管对那些已经熟悉材料的人（如这些帖子的作者）不满意，但对新手的入境造成了重大障碍。同样，我的目的是将各种模型（尽可能）吸收到一个用于推理和学习的框架上，表明（以及为什么）如何以最小的变化将一个模型更改为另一个模型（其中一些是新颖的，另一些是文献中的）。某些背景当然是必要的。我以为读者熟悉基本的多变量计算，概率和统计以及线性代数。这本书的目标当然不是​​完整性，而是从基本知识到过去十年中极强大的新模型的直线路径或多或少。然后，目标是补充而不是替换，诸如Bishop的\ emph {模式识别和机器学习}之类的综合文本，该文本现在已经15岁了。

We propose an efficient method for approximating natural gradient descent in neural networks which we call Kronecker-factored Approximate Curvature (K-FAC). K-FAC is based on an efficiently invertible approximation of a neural network's Fisher information matrix which is neither diagonal nor low-rank, and in some cases is completely non-sparse. It is derived by approximating various large blocks of the Fisher (corresponding to entire layers) as being the Kronecker product of two much smaller matrices. While only several times more expensive to compute than the plain stochastic gradient, the updates produced by K-FAC make much more progress optimizing the objective, which results in an algorithm that can be much faster than stochastic gradient descent with momentum in practice. And unlike some previously proposed approximate natural-gradient/Newton methods which use high-quality non-diagonal curvature matrices (such as Hessian-free optimization), K-FAC works very well in highly stochastic optimization regimes. This is because the cost of storing and inverting K-FAC's approximation to the curvature matrix does not depend on the amount of data used to estimate it, which is a feature typically associated only with diagonal or low-rank approximations to the curvature matrix.

我们提供了通过线性激活的多渠道卷积神经网络中的$ \ ell_2 $标准来最大程度地减少$ \ ell_2 $标准而产生的功能空间表征，并经验测试了我们对使用梯度下降训练的Relu网络的假设。我们将功能空间中的诱导正规化程序定义为实现函数所需的网络权重规范的最小$ \ ell_2 $。对于具有$ C $输出频道和内核尺寸$ K $的两个层线性卷积网络，我们显示以下内容：（a）如果网络的输入是单个渠道，则任何$ k $的诱导正规器都与数字无关输出频道$ c $。此外，我们得出正常化程序是由半决赛程序（SDP）给出的规范。 （b）相比之下，对于多通道输入，仅实现所有矩阵值值线性函数而需要多个输出通道，因此归纳偏置确实取决于$ c $。但是，对于足够大的$ c $，诱导的正规化程序再次由独立于$ c $的SDP给出。特别是，$ k = 1 $和$ k = d $（输入维度）的诱导正规器以封闭形式作为核标准和$ \ ell_ {2,1} $ group-sparse Norm，线性预测指标的傅立叶系数。我们通过对MNIST和CIFAR-10数据集的实验来研究理论结果对从线性和RELU网络上梯度下降的隐式正则化的更广泛的适用性。

这项调查的目的是介绍对深神经网络的近似特性的解释性回顾。具体而言，我们旨在了解深神经网络如何以及为什么要优于其他经典线性和非线性近似方法。这项调查包括三章。在第1章中，我们回顾了深层网络及其组成非线性结构的关键思想和概念。我们通过在解决回归和分类问题时将其作为优化问题来形式化神经网络问题。我们简要讨论用于解决优化问题的随机梯度下降算法以及用于解决优化问题的后传播公式，并解决了与神经网络性能相关的一些问题，包括选择激活功能，成本功能，过度适应问题和正则化。在第2章中，我们将重点转移到神经网络的近似理论上。我们首先介绍多项式近似中的密度概念，尤其是研究实现连续函数的Stone-WeierStrass定理。然后，在线性近似的框架内，我们回顾了馈电网络的密度和收敛速率的一些经典结果，然后在近似Sobolev函数中进行有关深网络复杂性的最新发展。在第3章中，利用非线性近似理论，我们进一步详细介绍了深度和近似网络与其他经典非线性近似方法相比的近似优势。

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.

These notes were compiled as lecture notes for a course developed and taught at the University of the Southern California. They should be accessible to a typical engineering graduate student with a strong background in Applied Mathematics. The main objective of these notes is to introduce a student who is familiar with concepts in linear algebra and partial differential equations to select topics in deep learning. These lecture notes exploit the strong connections between deep learning algorithms and the more conventional techniques of computational physics to achieve two goals. First, they use concepts from computational physics to develop an understanding of deep learning algorithms. Not surprisingly, many concepts in deep learning can be connected to similar concepts in computational physics, and one can utilize this connection to better understand these algorithms. Second, several novel deep learning algorithms can be used to solve challenging problems in computational physics. Thus, they offer someone who is interested in modeling a physical phenomena with a complementary set of tools.

The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and deep learning, covering advances in probabilistic models, auto-encoders, manifold learning, and deep networks. This motivates longer-term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation and manifold learning.

Consider the multivariate nonparametric regression model. It is shown that estimators based on sparsely connected deep neural networks with ReLU activation function and properly chosen network architecture achieve the minimax rates of convergence (up to log nfactors) under a general composition assumption on the regression function. The framework includes many well-studied structural constraints such as (generalized) additive models. While there is a lot of flexibility in the network architecture, the tuning parameter is the sparsity of the network. Specifically, we consider large networks with number of potential network parameters exceeding the sample size. The analysis gives some insights into why multilayer feedforward neural networks perform well in practice. Interestingly, for ReLU activation function the depth (number of layers) of the neural network architectures plays an important role and our theory suggests that for nonparametric regression, scaling the network depth with the sample size is natural. It is also shown that under the composition assumption wavelet estimators can only achieve suboptimal rates.

这是一门专门针对STEM学生开发的介绍性机器学习课程。我们的目标是为有兴趣的读者提供基础知识，以在自己的项目中使用机器学习，并将自己熟悉术语作为进一步阅读相关文献的基础。在这些讲义中，我们讨论受监督，无监督和强化学习。注释从没有神经网络的机器学习方法的说明开始，例如原理分析，T-SNE，聚类以及线性回归和线性分类器。我们继续介绍基本和先进的神经网络结构，例如密集的进料和常规神经网络，经常性的神经网络，受限的玻尔兹曼机器，（变性）自动编码器，生成的对抗性网络。讨论了潜在空间表示的解释性问题，并使用梦和对抗性攻击的例子。最后一部分致力于加强学习，我们在其中介绍了价值功能和政策学习的基本概念。

我们为特殊神经网络架构，称为运营商复发性神经网络的理论分析，用于近似非线性函数，其输入是线性运算符。这些功能通常在解决方案算法中出现用于逆边值问题的问题。传统的神经网络将输入数据视为向量，因此它们没有有效地捕获与对应于这种逆问题中的数据的线性运算符相关联的乘法结构。因此，我们介绍一个类似标准的神经网络架构的新系列，但是输入数据在向量上乘法作用。由较小的算子出现在边界控制中的紧凑型操作员和波动方程的反边值问题分析，我们在网络中的选择权重矩阵中促进结构和稀疏性。在描述此架构后，我们研究其表示属性以及其近似属性。我们还表明，可以引入明确的正则化，其可以从所述逆问题的数学分析导出，并导致概括属性上的某些保证。我们观察到重量矩阵的稀疏性改善了概括估计。最后，我们讨论如何将运营商复发网络视为深度学习模拟，以确定诸如用于从边界测量的声波方程中重建所未知的WAVESTED的边界控制的算法算法。

We present a new algorithm for automatically bounding the Taylor remainder series. In the special case of a scalar function $f: \mathbb{R} \mapsto \mathbb{R}$, our algorithm takes as input a reference point $x_0$, trust region $[a, b]$, and integer $k \ge 0$, and returns an interval $I$ such that $f(x) - \sum_{i=0}^k \frac {f^{(i)}(x_0)} {i!} (x - x_0)^i \in I (x - x_0)^{k+1}$ for all $x \in [a, b]$. As in automatic differentiation, the function $f$ is provided to the algorithm in symbolic form, and must be composed of known elementary functions. At a high level, our algorithm has two steps. First, for a variety of commonly-used elementary functions (e.g., $\exp$, $\log$), we derive sharp polynomial upper and lower bounds on the Taylor remainder series. We then recursively combine the bounds for the elementary functions using an interval arithmetic variant of Taylor-mode automatic differentiation. Our algorithm can make efficient use of machine learning hardware accelerators, and we provide an open source implementation in JAX. We then turn our attention to applications. Most notably, we use our new machinery to create the first universal majorization-minimization optimization algorithms: algorithms that iteratively minimize an arbitrary loss using a majorizer that is derived automatically, rather than by hand. Applied to machine learning, this leads to architecture-specific optimizers for training deep networks that converge from any starting point, without hyperparameter tuning. Our experiments show that for some optimization problems, these hyperparameter-free optimizers outperform tuned versions of gradient descent, Adam, and AdaGrad. We also show that our automatically-derived bounds can be used for verified global optimization and numerical integration, and to prove sharper versions of Jensen's inequality.

强大的机器学习模型的开发中的一个重要障碍是协变量的转变，当训练和测试集的输入分布时发生的分配换档形式在条件标签分布保持不变时发生。尽管现实世界应用的协变量转变普遍存在，但在现代机器学习背景下的理论理解仍然缺乏。在这项工作中，我们检查协变量的随机特征回归的精确高尺度渐近性，并在该设置中提出了限制测试误差，偏差和方差的精确表征。我们的结果激发了一种自然部分秩序，通过协变速转移，提供足够的条件来确定何时何时损害（甚至有助于）测试性能。我们发现，过度分辨率模型表现出增强的协会转变的鲁棒性，为这种有趣现象提供了第一个理论解释之一。此外，我们的分析揭示了分销和分发外概率性能之间的精确线性关系，为这一令人惊讶的近期实证观察提供了解释。

模型不足的元学习（MAML）已越来越流行，对于可以通过一个或几个随机梯度下降步骤迅速适应新任务的训练模型。但是，与标准的非自适应学习（NAL）相比，MAML目标更难优化，并且几乎没有理解MAML在各种情况下的溶液的快速适应性方面的改善。我们通过线性回归设置进行分析解决此问题，该设置由简单而艰难的任务组成，其中硬度与梯度下降在任务上收敛的速率有关。具体而言，我们证明，为了使MAML比NAL获得可观的收益，（i）任务之间的硬度必须有一定的差异，并且（ii）艰苦任务的最佳解决方案必须与中心远离远离中心。简单任务最佳解决方案的中心。我们还提供数值和分析结果，表明这些见解适用于两层神经网络。最后，我们提供了很少的图像分类实验，可以支持我们何时使用MAML的见解，并强调培训MAML对实践中的艰巨任务的重要性。

Modern machine learning requires system designers to specify aspects of the learning pipeline, such as losses, architectures, and optimizers. Meta-learning, or learning-to-learn, instead aims to learn those aspects, and promises to unlock greater capabilities with less manual effort. One particularly ambitious goal of meta-learning is to train general-purpose in-context learning algorithms from scratch, using only black-box models with minimal inductive bias. Such a model takes in training data, and produces test-set predictions across a wide range of problems, without any explicit definition of an inference model, training loss, or optimization algorithm. In this paper we show that Transformers and other black-box models can be meta-trained to act as general-purpose in-context learners. We characterize phase transitions between algorithms that generalize, algorithms that memorize, and algorithms that fail to meta-train at all, induced by changes in model size, number of tasks, and meta-optimization. We further show that the capabilities of meta-trained algorithms are bottlenecked by the accessible state size (memory) determining the next prediction, unlike standard models which are thought to be bottlenecked by parameter count. Finally, we propose practical interventions such as biasing the training distribution that improve the meta-training and meta-generalization of general-purpose learning algorithms.

这本数字本书包含在物理模拟的背景下与深度学习相关的一切实际和全面的一切。尽可能多，所有主题都带有Jupyter笔记本的形式的动手代码示例，以便快速入门。除了标准的受监督学习的数据中，我们将看看物理丢失约束，更紧密耦合的学习算法，具有可微分的模拟，以及加强学习和不确定性建模。我们生活在令人兴奋的时期：这些方法具有从根本上改变计算机模拟可以实现的巨大潜力。

Whilst deep neural networks have shown great empirical success, there is still much work to be done to understand their theoretical properties. In this paper, we study the relationship between random, wide, fully connected, feedforward networks with more than one hidden layer and Gaussian processes with a recursive kernel definition. We show that, under broad conditions, as we make the architecture increasingly wide, the implied random function converges in distribution to a Gaussian process, formalising and extending existing results by Neal (1996) to deep networks. To evaluate convergence rates empirically, we use maximum mean discrepancy. We then compare finite Bayesian deep networks from the literature to Gaussian processes in terms of the key predictive quantities of interest, finding that in some cases the agreement can be very close. We discuss the desirability of Gaussian process behaviour and review non-Gaussian alternative models from the literature. 1