深度学习的一个有前景的趋势取代了具有隐式网络的传统馈送网络。与传统网络不同,隐式网络解决了一个固定点方程来计算推断。解决固定点的复杂性变化,具体取决于提供的数据和误差容差。重要的是,可以通过与前馈网络的STARK对比度训练隐式网络,其内存需求与深度线性缩放。但是,没有免费的午餐 - 通过隐式网络锻造BackPropagation通常需要解决从隐式功能定理引起的昂贵的Jacobian等方程。我们提出了无雅各比的BackPropagation(JFB),一种固定内存方法,这些方法旨在解决基于雅略族裔的基于雅代族人的方程。 JFB使隐式网络更快地培训,并明显更容易实现,而不会牺牲测试精度。我们的实验表明,使用JFB培训的隐式网络与给出相同数量的参数的前馈网络和现有的隐式网络具有竞争力。
translated by 谷歌翻译
本文侧重于培训无限层的隐含模型。具体而言,以前的作品采用隐式差分,并解决后向传播的精确梯度。但是,是否有必要计算训练的这种精确但昂贵的渐变?在这项工作中,我们提出了一种新颖的梯度估计,用于隐式模型,命名为Phantom梯度,1)用于精确梯度的昂贵计算; 2)提供了对隐式模型培训的凭经质优选的更新方向。理论上,理论上可以分析可以找到损失景观的上升方向的条件,并基于阻尼展开和Neumann系列提供幻象梯度的两个特定实例化。大规模任务的实验表明,这些轻质幻像梯度大大加快了培训隐式模型中的后向往大约1.7倍,甚至基于想象成上的精确渐变来提高对方法的性能。
translated by 谷歌翻译
We present a new approach to modeling sequential data: the deep equilibrium model (DEQ). Motivated by an observation that the hidden layers of many existing deep sequence models converge towards some fixed point, we propose the DEQ approach that directly finds these equilibrium points via root-finding. Such a method is equivalent to running an infinite depth (weight-tied) feedforward network, but has the notable advantage that we can analytically backpropagate through the equilibrium point using implicit differentiation. Using this approach, training and prediction in these networks require only constant memory, regardless of the effective "depth" of the network. We demonstrate how DEQs can be applied to two state-of-the-art deep sequence models: self-attention transformers and trellis networks. On large-scale language modeling tasks, such as the WikiText-103 benchmark, we show that DEQs 1) often improve performance over these stateof-the-art models (for similar parameter counts); 2) have similar computational requirements to existing models; and 3) vastly reduce memory consumption (often the bottleneck for training large sequence models), demonstrating an up-to 88% memory reduction in our experiments. The code is available at https://github. com/locuslab/deq.
translated by 谷歌翻译
Normalizing flows provide a general mechanism for defining expressive probability distributions, only requiring the specification of a (usually simple) base distribution and a series of bijective transformations. There has been much recent work on normalizing flows, ranging from improving their expressive power to expanding their application. We believe the field has now matured and is in need of a unified perspective. In this review, we attempt to provide such a perspective by describing flows through the lens of probabilistic modeling and inference. We place special emphasis on the fundamental principles of flow design, and discuss foundational topics such as expressive power and computational trade-offs. We also broaden the conceptual framing of flows by relating them to more general probability transformations. Lastly, we summarize the use of flows for tasks such as generative modeling, approximate inference, and supervised learning.
translated by 谷歌翻译
神经普通微分方程(神经ODE)是残留神经网络(RESNETS)的连续类似物。我们研究了重新NET定义的离散动力学是否接近连续的神经颂歌。我们首先量化了Resnet的隐藏状态轨迹与其相应神经ODE的解之间的距离。我们的界限很紧,在负面的一侧,如果残留函数的深度不光滑,则不会以深度为0。在正面,我们表明这种平滑度是通过梯度下降来保留的,该梯度下降具有线性残留功能和足够小的初始损失的重新系统。它确保在n上以1的速率1均匀地沿速率1的速率和优化时间对极限神经的隐式正则化。作为我们分析的副产品,我们考虑使用不含内存的离散伴随方法来训练重新NET,通过通过网络的向后传动恢复激活,并证明该方法理论上在大深度上取得了成功,如果残留功能是带有输入的Lipschitz。然后,我们证明HEUN的方法是一种二阶Ode集成方案,当残留函数及其深度平滑时,使用伴随方法进行更好的梯度估计。我们通过实验验证我们的伴随方法在很大程度上取得了成功,并且Heun方法需要更少的层才能成功。我们最终成功地使用了伴随方法来微调非常深的重新连接,而无需残留层的内存消耗。
translated by 谷歌翻译
深度学习中的许多任务涉及优化\ emph {输入}到网络以最小化或最大化一些目标;示例包括在生成模型中的潜在空间上的优化,以匹配目标图像,或者对其进行对接扰动的前进扰动以恶化分类器性能。然而,执行这种优化是传统上的昂贵,因为它涉及完全向前和向后通过网络,每个梯度步骤。在单独的工作中,最近的研究线程已经开发了深度均衡(DEQ)模型,一类放弃传统网络深度的模型,而是通过找到单个非线性层的固定点来计算网络的输出。在本文中,我们表明这两个设置之间存在自然协同作用。虽然,对于这些优化问题的天真使用DEQs是昂贵的(由于计算每个渐变步骤所需的时间),我们可以利用基于梯度的优化可以\ emph {本身}作为一个固定点来利用这一事实迭代基本上提高整体速度。也就是说,我们\ EMPH {同时解决了DEQ固定点\ EMPH {和}在网络输入上优化,所有内容都在单个“增强”的DEQ模型中,共同编码原始网络和优化过程。实际上,程序足够快,使我们允许我们有效地\以传统地依赖于“内在”优化循环的任务的{Train} DEQ模型。我们在各种任务中展示了这种策略,例如培训生成模型,同时优化潜在代码,培训模型,以实现逆问题,如去噪,普及训练和基于梯度的元学习。
translated by 谷歌翻译
We show that standard ResNet architectures can be made invertible, allowing the same model to be used for classification, density estimation, and generation. Typically, enforcing invertibility requires partitioning dimensions or restricting network architectures. In contrast, our approach only requires adding a simple normalization step during training, already available in standard frameworks. Invertible ResNets define a generative model which can be trained by maximum likelihood on unlabeled data. To compute likelihoods, we introduce a tractable approximation to the Jacobian log-determinant of a residual block. Our empirical evaluation shows that invertible ResNets perform competitively with both stateof-the-art image classifiers and flow-based generative models, something that has not been previously achieved with a single architecture.
translated by 谷歌翻译
平衡系统是表达神经计算的有力方法。作为特殊情况,它们包括对神经科学和机器学习的最新兴趣模型,例如平衡复发性神经网络,深度平衡模型或元学习。在这里,我们提出了一个新的原则,用于学习具有时间和空间本地规则的此类系统。我们的原理将学习作为一个最不控制的问题,我们首先引入一个最佳控制器,以将系统带入解决方案状态,然后将学习定义为减少达到这种状态所需的控制量。我们表明,将学习信号纳入动力学作为最佳控制可以以先前未知的方式传输信用分配信息,避免将中间状态存储在内存中,并且不依赖无穷小的学习信号。在实践中,我们的原理可以使基于梯度的学习方法的强大绩效匹配,该方法应用于涉及复发性神经网络和元学习的一系列问题。我们的结果阐明了大脑如何学习并提供解决广泛的机器学习问题的新方法。
translated by 谷歌翻译
We introduce a new family of deep neural network models. Instead of specifying a discrete sequence of hidden layers, we parameterize the derivative of the hidden state using a neural network. The output of the network is computed using a blackbox differential equation solver. These continuous-depth models have constant memory cost, adapt their evaluation strategy to each input, and can explicitly trade numerical precision for speed. We demonstrate these properties in continuous-depth residual networks and continuous-time latent variable models. We also construct continuous normalizing flows, a generative model that can train by maximum likelihood, without partitioning or ordering the data dimensions. For training, we show how to scalably backpropagate through any ODE solver, without access to its internal operations. This allows end-to-end training of ODEs within larger models.
translated by 谷歌翻译
我们提出了特征神经常规差分方程(C节点),该框架用于扩展神经常规微分方程(节点)之外的缺点。虽然节点模型将潜在状态的演变为对颂歌的解决方案,但是所提出的C节点模拟了潜在的潜在的演变作为其特征的一阶准线性部分微分方程(PDE)的解决方案,定义为PDE减少到ODES的曲线。反过来,还原允许应用标准框架,以解决PDE设置的杂散。另外,所提出的框架可以作为现有节点架构的扩展来投用,从而允许使用现有的黑盒颂歌求解器。我们证明了C节点框架通过展示不能由节点表示的功能来扩展经典节点,而是由C节点表示。我们通过在许多合成和实际数据场景中展示其性能,进一步研究了C节点框架的功效。经验结果展示了CIFAR-10,SVHN和MNIST数据集的提出方法提供的改进,如类似的计算预算作为现有节点方法。
translated by 谷歌翻译
一类非平滑实践优化问题可以写成,以最大程度地减少平滑且部分平滑的功能。我们考虑了这种结构化问题,这些问题也取决于参数矢量,并研究了将其解决方案映射相对于参数的问题,该参数在灵敏度分析和参数学习选择材料问题中具有很大的应用。我们表明,在部分平滑度和其他温和假设下,近端分裂算法产生的序列的自动分化(AD)会收敛于溶液映射的衍生物。对于一种自动分化的变体,我们称定点自动分化(FPAD),我们纠正了反向模式AD的内存开销问题,此外,理论上提供了更快的收敛。我们从数值上说明了套索和组套索问题的AD和FPAD的收敛性和收敛速率,并通过学习正则化项来证明FPAD在原型实用图像deoise问题上的工作。
translated by 谷歌翻译
Neural ordinary differential equations (neural ODEs) have emerged as a novel network architecture that bridges dynamical systems and deep learning. However, the gradient obtained with the continuous adjoint method in the vanilla neural ODE is not reverse-accurate. Other approaches suffer either from an excessive memory requirement due to deep computational graphs or from limited choices for the time integration scheme, hampering their application to large-scale complex dynamical systems. To achieve accurate gradients without compromising memory efficiency and flexibility, we present a new neural ODE framework, PNODE, based on high-level discrete adjoint algorithmic differentiation. By leveraging discrete adjoint time integrators and advanced checkpointing strategies tailored for these integrators, PNODE can provide a balance between memory and computational costs, while computing the gradients consistently and accurately. We provide an open-source implementation based on PyTorch and PETSc, one of the most commonly used portable, scalable scientific computing libraries. We demonstrate the performance through extensive numerical experiments on image classification and continuous normalizing flow problems. We show that PNODE achieves the highest memory efficiency when compared with other reverse-accurate methods. On the image classification problems, PNODE is up to two times faster than the vanilla neural ODE and up to 2.3 times faster than the best existing reverse-accurate method. We also show that PNODE enables the use of the implicit time integration methods that are needed for stiff dynamical systems.
translated by 谷歌翻译
神经网络的经典发展主要集中在有限维欧基德空间或有限组之间的学习映射。我们提出了神经网络的概括,以学习映射无限尺寸函数空间之间的运算符。我们通过一类线性积分运算符和非线性激活函数的组成制定运营商的近似,使得组合的操作员可以近似复杂的非线性运算符。我们证明了我们建筑的普遍近似定理。此外,我们介绍了四类运算符参数化:基于图形的运算符,低秩运算符,基于多极图形的运算符和傅里叶运算符,并描述了每个用于用每个计算的高效算法。所提出的神经运营商是决议不变的:它们在底层函数空间的不同离散化之间共享相同的网络参数,并且可以用于零击超分辨率。在数值上,与现有的基于机器学习的方法,达西流程和Navier-Stokes方程相比,所提出的模型显示出卓越的性能,而与传统的PDE求解器相比,与现有的基于机器学习的方法有关的基于机器学习的方法。
translated by 谷歌翻译
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.
translated by 谷歌翻译
Normalizing Flows are generative models which produce tractable distributions where both sampling and density evaluation can be efficient and exact. The goal of this survey article is to give a coherent and comprehensive review of the literature around the construction and use of Normalizing Flows for distribution learning. We aim to provide context and explanation of the models, review current state-of-the-art literature, and identify open questions and promising future directions.
translated by 谷歌翻译
我们提出了一种新颖的二阶优化框架,用于训练新兴的深度连续时间模型,特别是神经常规方程(神经杂物杂物)。由于他们的训练已经涉及昂贵的梯度计算来通过求解向后ode,因此导出有效的二阶方法变得高度不变。然而,灵感来自最近的最佳控制(OC)对训练深网络的解释,我们表明,可以采用称为差分编程的特定连续时间oC方法,以获得同一O(1 )内存成本。我们进一步探索了二阶衍生品的低级别表示,并表明它导致借助基于Kronecker的分子化的有效的预处理更新。由此产生的方法 - 命名的snopt - 收敛于壁钟时间中的一阶基线的速度要快得多,并且改进仍然在各种应用中保持一致,例如,图像分类,生成流量和时间序列预测。我们的框架还实现了直接的架构优化,例如神经杂物的集成时间,具有二阶反馈策略,加强了OC视角作为深度学习中优化的原则性工具。我们的代码可在https://github.com/ghliu/snopt上获得。
translated by 谷歌翻译
随机偏微分方程(SPDES)是在随机性影响下模拟动态系统的选择的数学工具。通过将搜索SPDE的温和解决方案作为神经定点问题,我们介绍了神经SPDE模型,以便从部分观察到的数据中使用(可能随机)的PDE溶液运营商。我们的模型为两类物理启发神经架构提供了扩展。一方面,它延伸了神经CDES,SDES,RDE - RNN的连续时间类似物,因为即使当后者在无限尺寸状态空间中演变时,它也能够处理进入的顺序信息。另一方面,它扩展了神经运营商 - 神经网络的概括到函数空间之间的模型映射 - 因为它可以用于学习解决方案运算符$(U_0,\ xi)\ MapSto U $同时上的SPDES初始条件$ u_0 $和驾驶噪声$ \ xi $的实现。神经SPDE是不变的,它可以使用基于记忆有效的隐式分化的反向化的训练,并且一旦接受训练,其评估比传统求解器快3个数量级。在包括2D随机Navier-Stokes方程的各种半线性SPDES的实验证明了神经间隙如何能够以更好的准确性学习复杂的时空动态,并仅使用适度的培训数据与所有替代模型相比。
translated by 谷歌翻译
我们分析了通过梯度流通过自洽动力场理论训练的无限宽度神经网络中的特征学习。我们构建了确定性动力学阶参数的集合,该参数是内部产物内核,用于在成对的时间点中,每一层中隐藏的单位激活和梯度,从而减少了通过训练对网络活动的描述。这些内核顺序参数共同定义了隐藏层激活分布,神经切线核的演变以及因此输出预测。我们表明,现场理论推导恢复了从Yang和Hu(2021)获得张量程序的无限宽度特征学习网络的递归随机过程。对于深线性网络,这些内核满足一组代数矩阵方程。对于非线性网络,我们提供了一个交替的采样过程,以求助于内核顺序参数。我们提供了与各种近似方案的自洽解决方案的比较描述。最后,我们提供了更现实的设置中的实验,这些实验表明,在CIFAR分类任务上,在不同宽度上保留了CNN的CNN的损耗和内核动力学。
translated by 谷歌翻译
本文介绍了OptNet,该网络架构集成了优化问题(这里,专门以二次程序的形式),作为较大端到端可训练的深网络中的单个层。这些层在隐藏状态之间编码约束和复杂依赖性,传统的卷积和完全连接的层通常无法捕获。我们探索这种架构的基础:我们展示了如何使用敏感性分析,彼得优化和隐式差分的技术如何通过这些层和相对于层参数精确地区分;我们为这些层开发了一种高效的解算器,用于利用基于GPU的基于GPU的批处理在原始 - 双内部点法中解决,并且在求解的顶部几乎没有额外的成本提供了反向衰减梯度;我们突出了这些方法在几个问题中的应用。在一个值得注意的示例中,该方法学习仅在输入和输出游戏中播放Mini-sudoku(4x4),没有关于游戏规则的a-priori信息;这突出了OptNet比其他神经架构更好地学习硬限制的能力。
translated by 谷歌翻译
找到模型的最佳超参数可以作为双重优化问题,通常使用零级技术解决。在这项工作中,当内部优化问题是凸但不平滑时,我们研究一阶方法。我们表明,近端梯度下降和近端坐标下降序列序列的前向模式分化,雅各比人会收敛到精确的雅各布式。使用隐式差异化,我们表明可以利用内部问题的非平滑度来加快计算。最后,当内部优化问题大约解决时,我们对高度降低的误差提供了限制。关于回归和分类问题的结果揭示了高参数优化的计算益处,尤其是在需要多个超参数时。
translated by 谷歌翻译