从非规范目标分布中抽样是概率推断中许多应用的基本问题。 Stein变异梯度下降(SVGD)已被证明是一种强大的方法,它迭代地更新一组粒子以近似关注的分布。此外,在分析其渐近性特性时,SVGD会准确地减少到单目标优化问题,并可以看作是此单目标优化问题的概率版本。然后出现一个自然的问题:“我们可以得出多目标优化的概率版本吗?”。为了回答这个问题,我们提出了随机多重目标采样梯度下降(MT-SGD),从而使我们能够从多个非差异目标分布中采样。具体而言,我们的MT-SGD进行了中间分布的流动,逐渐取向多个目标分布,这使采样颗粒可以移动到目标分布的关节高样区域。有趣的是,渐近分析表明,正如预期的那样,我们的方法准确地减少了多级下降算法以进行多目标优化。最后,我们进行全面的实验,以证明我们进行多任务学习方法的优点。
translated by 谷歌翻译
We propose a general purpose variational inference algorithm that forms a natural counterpart of gradient descent for optimization. Our method iteratively transports a set of particles to match the target distribution, by applying a form of functional gradient descent that minimizes the KL divergence. Empirical studies are performed on various real world models and datasets, on which our method is competitive with existing state-of-the-art methods. The derivation of our method is based on a new theoretical result that connects the derivative of KL divergence under smooth transforms with Stein's identity and a recently proposed kernelized Stein discrepancy, which is of independent interest.
translated by 谷歌翻译
Pareto Front Learning (PFL) was recently introduced as an effective approach to obtain a mapping function from a given trade-off vector to a solution on the Pareto front, which solves the multi-objective optimization (MOO) problem. Due to the inherent trade-off between conflicting objectives, PFL offers a flexible approach in many scenarios in which the decision makers can not specify the preference of one Pareto solution over another, and must switch between them depending on the situation. However, existing PFL methods ignore the relationship between the solutions during the optimization process, which hinders the quality of the obtained front. To overcome this issue, we propose a novel PFL framework namely \ourmodel, which employs a hypernetwork to generate multiple solutions from a set of diverse trade-off preferences and enhance the quality of the Pareto front by maximizing the Hypervolume indicator defined by these solutions. The experimental results on several MOO machine learning tasks show that the proposed framework significantly outperforms the baselines in producing the trade-off Pareto front.
translated by 谷歌翻译
最近的多任务学习研究旨在反对单一的标准化,其中培训只需最大限度地减少任务损失的总和。代替了几种Ad-hoc多任务优化算法,它受到各种假设的启发,关于使多任务设置困难的原因。这些优化器中的大多数都需要每个任务渐变,并引入重要的内存,运行时和实现开销。我们提出了一个理论分析,表明许多专业的多任务优化器可以被解释为正规化的形式。此外,我们表明,当与单任务学习的标准正则化和稳定技术耦合时,单一的标定化匹配或改善在监督和加固学习设置中复杂的多任务优化器的性能。我们相信我们的结果要求对该地区最近的研究进行关键重新评估。
translated by 谷歌翻译
In multi-task learning, multiple tasks are solved jointly, sharing inductive bias between them. Multi-task learning is inherently a multi-objective problem because different tasks may conflict, necessitating a trade-off. A common compromise is to optimize a proxy objective that minimizes a weighted linear combination of pertask losses. However, this workaround is only valid when the tasks do not compete, which is rarely the case. In this paper, we explicitly cast multi-task learning as multi-objective optimization, with the overall objective of finding a Pareto optimal solution. To this end, we use algorithms developed in the gradient-based multiobjective optimization literature. These algorithms are not directly applicable to large-scale learning problems since they scale poorly with the dimensionality of the gradients and the number of tasks. We therefore propose an upper bound for the multi-objective loss and show that it can be optimized efficiently. We further prove that optimizing this upper bound yields a Pareto optimal solution under realistic assumptions. We apply our method to a variety of multi-task deep learning problems including digit classification, scene understanding (joint semantic segmentation, instance segmentation, and depth estimation), and multilabel classification. Our method produces higher-performing models than recent multi-task learning formulations or per-task training.
translated by 谷歌翻译
贝叶斯优化(BO)算法在涉及昂贵的黑盒功能的应用中表现出了显着的成功。传统上,BO被设置为一个顺序决策过程,该过程通过采集函数和先前的功能(例如高斯过程)来估计查询点的实用性。然而,最近,通过密度比率估计(BORE)对BO进行重新制定允许将采集函数重新诠释为概率二进制分类器,从而消除了对函数的显式先验和提高可伸缩性的需求。在本文中,我们介绍了对孔的遗憾和算法扩展的理论分析,并提高了不确定性估计。我们还表明,通过将问题重新提交为近似贝叶斯推断,可以自然地扩展到批处理优化设置。所得算法配备了理论性能保证,并在一系列实验中对其他批处理基本线进行了评估。
translated by 谷歌翻译
许多现代的机器学习应用程序,例如多任务学习,都需要查找最佳模型参数来权衡多个可能相互冲突的目标功能。帕累托集的概念使我们能够专注于不能严格改进的(通常是无限的)模型集。但是,它不能为选择一个或几个特殊型号返回实际用户提供可行的程序。在本文中,我们考虑\ emph {在Pareto Set(Opt-In-Pareto)中进行优化,这是找到Pareto模型,以优化Pareto集中的额外参考标准函数。此功能可以编码从用户的特定偏好,也可以代表代表整个帕累托集的一组多元化的帕累托模型来代表一组多元化的帕累托模型。不幸的是,尽管是一个非常有用的框架,但在深度学习中,尤其是对于大规模,非凸面和非线性目标而言,对选择性pareto的有效算法已经很大程度上遗失了。一种幼稚的方法是将Riemannian歧管梯度下降应用于帕累托集,该片段由于需要对Hessian矩阵的本征估计而产生高计算成本。我们提出了一种一阶算法,该算法仅使用梯度信息近似求解pareto,具有高实用效率和理论上保证的收敛属性。从经验上讲,我们证明我们的方法在各种具有挑战性的多任务相关问题方面有效地工作。
translated by 谷歌翻译
变性推理(VI)为基于传统的采样方法提供了一种吸引人的替代方法,用于实施贝叶斯推断,因为其概念性的简单性,统计准确性和计算可扩展性。然而,常见的变分近似方案(例如平均场(MF)近似)需要某些共轭结构以促进有效的计算,这可能会增加不必要的限制对可行的先验分布家族,并对变异近似族对差异进行进一步的限制。在这项工作中,我们开发了一个通用计算框架,用于实施MF-VI VIA WASSERSTEIN梯度流(WGF),这是概率度量空间上的梯度流。当专门针对贝叶斯潜在变量模型时,我们将分析基于时间消化的WGF交替最小化方案的算法收敛,用于实现MF近似。特别是,所提出的算法类似于EM算法的分布版本,包括更新潜在变量变异分布的E step以及在参数的变异分布上进行最陡峭下降的m step。我们的理论分析依赖于概率度量空间中的最佳运输理论和细分微积分。我们证明了时间限制的WGF的指数收敛性,以最大程度地减少普通大地测量学严格的凸度的通用物镜功能。我们还提供了通过使用时间限制的WGF的固定点方程从MF近似获得的变异分布的指数收缩的新证明。我们将方法和理论应用于两个经典的贝叶斯潜在变量模型,即高斯混合模型和回归模型的混合物。还进行了数值实验,以补充这两个模型下的理论发现。
translated by 谷歌翻译
贝叶斯神经网络(BNNS)已成为缓解深度学习中过度自信预测的主要方法,但由于大量分布参数,它们经常遭受扩展问题。在本文中,我们发现在单独再培训时,深网络的第一层拥有多个不同的Optima。这表示当第一层由贝叶斯层改变时的大后差,这使我们能够设计空间融合BNN(STF-BNN),以便有效地将BNN缩放到大型模型:(1)首先常常培训一个神经网络网络从头开始实现快速训练; (2)第一层被转换为贝叶斯和通过采用随机变分推断推断,而其他层是固定的。与香草BNN相比,我们的方法可以大大减少训练时间和参数的数量,这有助于高效地缩放BNN。我们进一步提供了对概括性和缓解STF-BNN过度限制的能力的理论保障。综合实验表明,STF-BNN(1)实现了最先进的性能,以进行预测和不确定量化; (2)显着提高对抗性鲁棒性和隐私保护; (3)大大降低了培训时间和内存成本。
translated by 谷歌翻译
我们提出了一个统一的查看,即通过通用表示,一个深层神经网络共同学习多个视觉任务和视觉域。同时学习多个问题涉及最大程度地减少具有不同幅度和特征的多个损失函数的加权总和,从而导致一个损失的不平衡状态,与学习每个问题的单独模型相比,一个损失的不平衡状态主导了优化和差的结果。为此,我们提出了通过小容量适配器将多个任务/特定于域网络的知识提炼到单个深神经网络中的知识。我们严格地表明,通用表示在学习NYU-V2和CityScapes中多个密集的预测问题方面实现了最新的表现,来自视觉Decathlon数据集中的不同域中的多个图像分类问题以及MetadataSet中的跨域中的几个域中学习。最后,我们还通过消融和定性研究进行多次分析。
translated by 谷歌翻译
我们引入了重新定性,这是一种数据依赖性的重新聚集化,将贝叶斯神经网络(BNN)转化为后部的分布,其KL对BNN对BNN的差异随着层宽度的增长而消失。重新定义图直接作用于参数,其分析简单性补充了宽BNN在功能空间中宽BNN的已知神经网络过程(NNGP)行为。利用重新定性,我们开发了马尔可夫链蒙特卡洛(MCMC)后采样算法,该算法将BNN更快地混合在一起。这与MCMC在高维度上的表现差异很差。对于完全连接和残留网络,我们观察到有效样本量高达50倍。在各个宽度上都取得了改进,并在层宽度的重新培训和标准BNN之间的边缘。
translated by 谷歌翻译
现代深度学习方法构成了令人难以置信的强大工具,以解决无数的挑战问题。然而,由于深度学习方法作为黑匣子运作,因此与其预测相关的不确定性往往是挑战量化。贝叶斯统计数据提供了一种形式主义来理解和量化与深度神经网络预测相关的不确定性。本教程概述了相关文献和完整的工具集,用于设计,实施,列车,使用和评估贝叶斯神经网络,即使用贝叶斯方法培训的随机人工神经网络。
translated by 谷歌翻译
Bootstrap是一种用于不确定性定量的原则性且强大的频繁统计工具。不幸的是,由于需要绘制大型i.i.d。引导样品近似理想的引导分布;这在很大程度上阻碍了他们在大型机器学习中的应用,尤其是深度学习问题。在这项工作中,我们提出了一种有效的方法,可以明确\ emph {优化}一小部分高质量的``centroid''指向,以更好地近似理想的引导分布。我们通过最大程度地减少一个简单的目标函数来实现这一目标,该目标函数渐近地等同于Wasserstein距离与理想的引导分布。这使我们能够通过少量的自举质心提供准确的不确定性估计,表现优于天真的I.I.I.D.采样方法。从经验上讲,我们表明我们的方法可以在各种应用中提高引导性的性能。
translated by 谷歌翻译
我们开发了一个探索漏洞利用马尔可夫链Monte Carlo算法($ \ OperatorName {ex ^ 2mcmc} $),它结合了多个全局提议和本地移动。所提出的方法是巨大的平行化和极其计算的高效。我们证明$ \ operatorname {ex ^ 2mcmc} $下的$ v $ v $ -unique几何ergodicity在现实条件下,并计算混合速率的显式界限,显示多个全局移动带来的改进。我们展示$ \ operatorname {ex ^ 2mcmc} $允许通过提出依赖全局移动的新方法进行微调剥削(本地移动)和探索(全球移动)。最后,我们开发了一个自适应方案,$ \ OperatorName {Flex ^ 2mcmc} $,它学习使用归一化流的全局动作的分布。我们说明了许多经典采样基准测试的$ \ OperatorName {ex ^ 2mccmc} $及其自适应版本的效率。我们还表明,这些算法提高了对基于能量的模型的抽样GAN的质量。
translated by 谷歌翻译
在多任务学习(MTL)中,对联合模型进行了培训,可以同时对几个任务进行预测。联合培训降低了计算成本并提高数据效率;但是,由于这些不同任务的梯度可能需要冲突,因此训练MTL的联合模型通常比其相应的单任务对应人员产生的性能较低。减轻此问题的一种常见方法是使用特定的启发式方法将每个任务梯度组合到联合更新方向上。在本文中,我们建议将梯度组合步骤视为一个议价游戏,在该游戏中,任务就达成了有关参数更新联合方向的协议。在某些假设下,议价问题具有独特的解决方案,称为NASH讨价还价解决方案,我们建议将其用作多任务学习的原则方法。我们描述了一种新的MTL优化程序NASH-MTL,并为其收敛性得出了理论保证。从经验上讲,我们表明NASH-MTL在各个域中的多个MTL基准上实现了最新的结果。
translated by 谷歌翻译
我们专注于具有单个隐藏层的特定浅神经网络,即具有$ 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。
translated by 谷歌翻译
桥梁采样是一种强大的蒙特卡洛方法,用于估计标准化常数的比率。引入了各种方法以提高其效率。这些方法旨在通过对它们应用适当的转换而不更改标准化常数来增加密度之间的重叠。在本文中,我们首先给出了最佳桥梁估计器的渐近相对平方误差(RMSE)的新估计器,通过等效地估计两个密度之间的$ f $差异。然后,我们利用此框架,并根据二元式转换提出$ f $ -gan桥估计器($ f $ -GB),该框架将一个密度映射到另一个密度,并最小化最佳桥梁估计器的渐近RMSE相对于密度。通过使用$ f $ gan之间的密度之间的特定$ f $ divergence来选择这种转换。从某种意义上说,在任何给定的候选转换中,$ f $ -GB估算器可以渐近地实现比桥梁估算器低于或等于由任何其他转换的密度低的RMSE,我们显示出$ f $ -GB是最佳的。数值实验表明,$ f $ -GB在模拟和现实世界中的现有方法优于现有方法。此外,我们讨论了桥梁估计器如何自然来自$ f $ divergence估计的问题。
translated by 谷歌翻译
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
translated by 谷歌翻译
Multilevel Stein variational gradient descent is a method for particle-based variational inference that leverages hierarchies of approximations of target distributions with varying costs and fidelity to computationally speed up inference. This work provides a cost complexity analysis of multilevel Stein variational gradient descent that applies under milder conditions than previous results, especially in discrete-in-time regimes and beyond the limited settings where Stein variational gradient descent achieves exponentially fast convergence. The analysis shows that the convergence rate of Stein variational gradient descent enters only as a constant factor for the cost complexity of the multilevel version, which means that the costs of the multilevel version scale independently of the convergence rate of Stein variational gradient descent on a single level. Numerical experiments with Bayesian inverse problems of inferring discretized basal sliding coefficient fields of the Arolla glacier ice demonstrate that multilevel Stein variational gradient descent achieves orders of magnitude speedups compared to its single-level version.
translated by 谷歌翻译
Distributed Stein Variational Gradient Descent (DSVGD) is a non-parametric distributed learning framework for federated Bayesian learning, where multiple clients jointly train a machine learning model by communicating a number of non-random and interacting particles with the server. Since communication resources are limited, selecting the clients with most informative local learning updates can improve the model convergence and communication efficiency. In this paper, we propose two selection schemes for DSVGD based on Kernelized Stein Discrepancy (KSD) and Hilbert Inner Product (HIP). We derive the upper bound on the decrease of the global free energy per iteration for both schemes, which is then minimized to speed up the model convergence. We evaluate and compare our schemes with conventional schemes in terms of model accuracy, convergence speed, and stability using various learning tasks and datasets.
translated by 谷歌翻译