使用通过组成可逆层获得的地图进行标准化模型复杂概率分布。特殊的线性层(例如蒙版和1x1卷积)在现有体系结构中起着关键作用,因为它们在具有可拖动的Jacobians和倒置的同时增加表达能力。我们提出了一个基于蝴蝶层的新的可逆线性层家族,理论上捕获复杂的线性结构,包括排列和周期性,但可以有效地倒置。这种代表力是我们方法的关键优势,因为这些结构在许多现实世界数据集中很常见。根据我们的可逆蝴蝶层,我们构建了一个新的称为蝴蝶流的归一化流量模型。从经验上讲,我们证明蝴蝶不仅可以在MNIST,CIFAR-10和Imagenet 32​​x32等自然图像上实现强密度估计结果,而且还可以在结构化数据集中获得明显更好的对数可能性,例如Galaxy图像和Mimic-III患者群体 - - 同时,在记忆和计算方面比相关基线更有效。
translated by 谷歌翻译
基于流量的生成模型最近已成为模拟数据生成的最有效方法之一。实际上,它们是由一系列可逆和可触觉转换构建的。Glow首先使用可逆$ 1 \ times 1 $卷积引入了一种简单的生成流。但是,与标准卷积相比,$ 1 \ times 1 $卷积的灵活性有限。在本文中,我们提出了一种新颖的可逆$ n \ times n $卷积方法,该方法克服了可逆$ 1 \ times 1 $卷积的局限性。此外,我们所提出的网络不仅可以处理和可逆,而且比标准卷积使用的参数少。CIFAR-10,ImageNet和Celeb-HQ数据集的实验表明,我们可逆的$ N \ times n $卷积有助于显着提高生成模型的性能。
translated by 谷歌翻译
A normalizing flow models a complex probability density as an invertible transformation of a simple base density. Flows based on either coupling or autoregressive transforms both offer exact density evaluation and sampling, but rely on the parameterization of an easily invertible elementwise transformation, whose choice determines the flexibility of these models. Building upon recent work, we propose a fully-differentiable module based on monotonic rational-quadratic splines, which enhances the flexibility of both coupling and autoregressive transforms while retaining analytic invertibility. We demonstrate that neural spline flows improve density estimation, variational inference, and generative modeling of images.
translated by 谷歌翻译
Normalizing Flows are generative models which produce tractable distributions where both sampling and density evaluation can be efficient and exact. The goal of this survey article is to give a coherent and comprehensive review of the literature around the construction and use of Normalizing Flows for distribution learning. We aim to provide context and explanation of the models, review current state-of-the-art literature, and identify open questions and promising future directions.
translated by 谷歌翻译
生成建模旨在揭示产生观察到的数据的潜在因素,这些数据通常可以被建模为自然对称性,这些对称性是通过不变和对某些转型定律等效的表现出来的。但是,当前代表这些对称性的方法是在需要构建模棱两可矢量场的连续正式化流中所掩盖的 - 抑制了它们在常规的高维生成建模域(如自然图像)中的简单应用。在本文中,我们专注于使用离散层建立归一化流量。首先,我们从理论上证明了对紧凑空间的紧凑型组的模棱两可的图。我们进一步介绍了三个新的品牌流:$ g $ - 剩余的流量,$ g $ - 耦合流量和$ g $ - inverse自动回旋的回旋流量,可以提升经典的残留剩余,耦合和反向自动性流量,并带有等效的地图, $。从某种意义上说,我们证明$ g $ equivariant的差异性可以通过$ g $ - $ residual流量映射,我们的$ g $ - 剩余流量也很普遍。最后,我们首次在诸如CIFAR-10之类的图像数据集中对我们的理论见解进行了补充,并显示出$ G $ equivariant有限的有限流量,从而提高了数据效率,更快的收敛性和提高的可能性估计。
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
Flow-based generative models (Dinh et al., 2014) are conceptually attractive due to tractability of the exact log-likelihood, tractability of exact latent-variable inference, and parallelizability of both training and synthesis. In this paper we propose Glow, a simple type of generative flow using an invertible 1 × 1 convolution. Using our method we demonstrate a significant improvement in log-likelihood on standard benchmarks. Perhaps most strikingly, we demonstrate that a generative model optimized towards the plain log-likelihood objective is capable of efficient realisticlooking synthesis and manipulation of large images. The code for our model is available at https://github.com/openai/glow.
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
正常化流动在过去几年中已经变得更加流行;然而,他们继续计算得昂贵,使得它们难以被接受到更广泛的机器学习界中。在本文中,我们介绍了一个简单的一维一层网络,其封闭形式的Lipschitz常数;使用此,我们介绍了一种新的精确嘴唇流(ELF),这些流量(ELF)结合了剩余流量的易于采样,并具有自回归流的强烈性能。此外,我们表明,与多个其他流相比,ELF被证明是通用密度近似器,更新和参数有效,并且在多个大规模数据集上实现最先进的性能。
translated by 谷歌翻译
归一化流量是漫射的,通常是维持尺寸保存,使用模型的可能性训练的模型。我们使用Surve Framework通过新的层构建尺寸减少调节流量,称为漏斗。我们展示了对各种数据集的功效,并表明它改善或匹配现有流量的性能,同时具有降低的潜在空间尺寸。漏斗层可以由各种变换构成,包括限制卷积和馈送前部。
translated by 谷歌翻译
标准化流是生成模型,其通过从简单的基本分布到复杂的目标分布的可逆性转换提供易于变换的工艺模型。然而,该技术不能直接模拟支持未知的低维歧管的数据,在诸如图像数据之类的现实世界域中的公共发生。最近的补救措施的尝试引入了击败归一化流量的中央好处的几何并发症:精确密度估计。我们通过保形嵌入流量来恢复这种福利,这是一种设计流动与贸易密度的流动的流动的框架。我们争辩说,使用培训保育嵌入的标准流量是模型支持数据的最自然的方式。为此,我们提出了一系列保形构建块,并在具有合成和实际数据的实验中应用它们,以证明流动可以在不牺牲贸易可能性的情况下模拟歧管支持的分布。
translated by 谷歌翻译
归一化流量是输入和潜在表示之间的基础映射,具有完全分解的分布。由于精确的可能性估值和有效的抽样,它们非常有吸引力。然而,由于杀硅约束限制了模型宽度,因此它们的有效容量通常不足。我们通过逐渐填充噪音的中间表示来解决此问题。我们根据先前可逆的单位预处理噪声,我们将其描述为交叉单元耦合。我们可逆的发光模块通过融合具有腹部自我关注的密集连接块来提高模型表达性。我们将我们的体系结构称为致密流,因为跨单元和模块内联轴器都依赖于密集的连接。实验表现出显着的改善,因为拟议的贡献和揭示了中等计算预算下的最先进的密度估算。
translated by 谷歌翻译
Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning. Specifically, designing models with tractable learning, sampling, inference and evaluation is crucial in solving this task. We extend the space of such models using real-valued non-volume preserving (real NVP) transformations, a set of powerful, stably invertible, and learnable transformations, resulting in an unsupervised learning algorithm with exact log-likelihood computation, exact and efficient sampling, exact and efficient inference of latent variables, and an interpretable latent space. We demonstrate its ability to model natural images on four datasets through sampling, log-likelihood evaluation, and latent variable manipulations.
translated by 谷歌翻译
Autoregressive models are among the best performing neural density estimators. We describe an approach for increasing the flexibility of an autoregressive model, based on modelling the random numbers that the model uses internally when generating data. By constructing a stack of autoregressive models, each modelling the random numbers of the next model in the stack, we obtain a type of normalizing flow suitable for density estimation, which we call Masked Autoregressive Flow. This type of flow is closely related to Inverse Autoregressive Flow and is a generalization of Real NVP. Masked Autoregressive Flow achieves state-of-the-art performance in a range of general-purpose density estimation tasks.
translated by 谷歌翻译
我们提出了一个利用归一化流的拓扑非平凡流形的学习概率分布的框架。当前的方法集中在对欧几里得空间同质形态的流形上,在学习模型上执行强大的结构先验或不容易扩展到高维度的操作。相比之下,我们的方法通过将多个局部模型“粘合”一起学习数据歧管上的分布,从而定义了数据歧管的开放覆盖。我们证明了我们的方法在已知流形的合成数据以及未知拓扑的较高维歧管上的效率,在许多任务中,我们的方法在许多任务中表现出更好的样品效率和竞争性或优越的性能。
translated by 谷歌翻译
尽管对连续数据的归一流流进行了广泛的研究,但直到最近才探索了离散数据的流量。然而,这些先前的模型遭受了与连续流的局限性。最值得注意的是,由于离散函数的梯度不确定或零,因此不能直接优化基于流动的模型。先前的作品近似离散功能的伪级,但不能在基本层面上解决该问题。除此之外,与替代离散算法(例如决策树算法)相比,反向传播可能是计算繁重的。我们的方法旨在减轻计算负担,并通过基于决策树开发离散流程来消除对伪级的需求,这是基于有效的基于树的基于有效的树的方法进行分类和回归的离散数据。我们首先定义了树结构化置换(TSP),该置换量(TSP)紧凑地编码离散数据的排列,其中逆向易于计算;因此,我们可以有效地计算密度值并采样新数据。然后,我们提出了一种决策树算法来构建TSP,该TSP通过新标准在每个节点上学习树结构和排列。我们从经验上证明了我们在多个数据集上方法的可行性。
translated by 谷歌翻译
A neural network deployed in the wild may be asked to make predictions for inputs that were drawn from a different distribution than that of the training data. A plethora of work has demonstrated that it is easy to find or synthesize inputs for which a neural network is highly confident yet wrong. Generative models are widely viewed to be robust to such mistaken confidence as modeling the density of the input features can be used to detect novel, out-of-distribution inputs. In this paper we challenge this assumption. We find that the density learned by flow-based models, VAEs, and PixelCNNs cannot distinguish images of common objects such as dogs, trucks, and horses (i.e. CIFAR-10) from those of house numbers (i.e. SVHN), assigning a higher likelihood to the latter when the model is trained on the former. Moreover, we find evidence of this phenomenon when pairing several popular image data sets: FashionMNIST vs MNIST, CelebA vs SVHN, ImageNet vs CIFAR-10 / CIFAR-100 / SVHN. To investigate this curious behavior, we focus analysis on flow-based generative models in particular since they are trained and evaluated via the exact marginal likelihood. We find such behavior persists even when we restrict the flows to constant-volume transformations. These transformations admit some theoretical analysis, and we show that the difference in likelihoods can be explained by the location and variances of the data and the model curvature. Our results caution against using the density estimates from deep generative models to identify inputs similar to the training distribution until their behavior for out-of-distribution inputs is better understood.
translated by 谷歌翻译
可逆的神经网络(Inns)已被用于设计生成模型,实现节省内存梯度计算,并解决逆问题。在这项工作中,我们展示了普通二手纪念架构遭受爆炸逆,因此易于变得数值不可逆转。在广泛的Inn用例中,我们揭示了包括在分配和分配的变化(OOD)数据的变化公式的不适用性的失败,用于节省内存返回的不正确渐变,以及无法从标准化流量模型中采样。我们进一步推出了普通架构原子构建块的双嘴唇特性。这些见解对旅馆的稳定性然后提供了前进的方法来解决这些故障。对于本地可释放足够的任务,如记忆保存的倒退,我们提出了一种灵活且高效的常规器。对于必要的全球可逆性的问题,例如在ood数据上应用标准化流动,我们展示了设计稳定的旅馆构建块的重要性。
translated by 谷歌翻译
现在,存储快速增长的大数据是不可取的,这需要高性能的无损压缩技术。基于可能性的生成模型在无损压缩中获得了成功,其中基于流基的模型在允许与映射映射进行精确的数据似然优化时是可取的。然而,常见的连续流是矛盾的,并且编码方案的离散性,这需要1)对流量模型的严格约束来降低性能或2)编码许多减少效率的诸多的映射误差。在本文中,我们调查了对无损压缩的音量保持流动,并显示了一个没有错误的自由度映射。我们提出了来自总体积保护流的数值可释放的流量(IVPF)。通过在流模型上引入新颖的计算算法,在没有任何数值误差的情况下实现精确的映射映射。我们还提出了一种基于IVPF的无损压缩算法。各种数据集的实验表明,基于IVPF的算法通过轻量级压缩算法实现了最先进的压缩比。
translated by 谷歌翻译
离散和连续分布之间的映射是一项艰巨的任务,许多人不得不诉诸启发方法。我们提出了一种基于镶嵌的方法,该方法直接学习连续空间中的量化边界,并具有精确的可能性评估。这是通过使用具有有效的对数决定性jacobian的简单同态形态来构建凸多属凸的归一化流程来完成的。我们在两个应用程序设置中探索了这种方法,从离散到连续的映射,反之亦然。首先,Voronoi的消除化允许在多维空间中自动学习量化边界。边界的位置和区域之间的距离可以编码量化离散值之间的有用的结构关系。其次,无论混合组件的数量如何,Voronoi混合模型都具有恒定的计算成本,可用于可能性评估。从经验上讲,我们显示了对一系列结构化数据模式的现有方法的改进。
translated by 谷歌翻译