通过将域知识与标记的样本集成在一起,知情的机器学习已经出现,以提高广泛应用的学习绩效。尽管如此,对注射领域知识的作用的严格理解尚未探索。在本文中,我们考虑了一个知情的深度神经网络(DNN),并将过度参数化和域知识纳入其培训目标功能,并研究域知识如何以及为什么会使绩效受益。具体而言,我们定量地证明了领域知识的两个好处在知情学习中 - 正规化基于标签的监督并补充标签样品 - 并揭示了人口风险的标签和知识不完美性之间的权衡。基于理论分析,我们提出了一个广义知情的培训目标,以更好地利用知识的好处,并平衡标签和知识不完美,这是由人口风险约束的验证。我们对抽样复杂性的分析阐明了如何选择超参数进行知情学习的灯光,并进一步证明了知识知情学习的优势。
translated by 谷歌翻译
在本文中,我们利用过度参数化来设计高维单索索引模型的无规矩算法,并为诱导的隐式正则化现象提供理论保证。具体而言,我们研究了链路功能是非线性且未知的矢量和矩阵单索引模型,信号参数是稀疏向量或低秩对称矩阵,并且响应变量可以是重尾的。为了更好地理解隐含正规化的角色而没有过度的技术性,我们假设协变量的分布是先验的。对于载体和矩阵设置,我们通过采用分数函数变换和专为重尾数据的强大截断步骤来构造过度参数化最小二乘损耗功能。我们建议通过将无规则化的梯度下降应用于损耗函数来估计真实参数。当初始化接近原点并且步骤中足够小时,我们证明了所获得的解决方案在载体和矩阵案件中实现了最小的收敛统计速率。此外,我们的实验结果支持我们的理论调查结果,并表明我们的方法在$ \ ell_2 $ -staticatisticated率和变量选择一致性方面具有明确的正则化的经验卓越。
translated by 谷歌翻译
成功的深度学习模型往往涉及培训具有比训练样本数量更多的参数的神经网络架构。近年来已经广泛研究了这种超分子化的模型,并且通过双下降现象和通过优化景观的结构特性,从统计的角度和计算视角都建立了过分统计化的优点。尽管在过上分层的制度中深入学习架构的显着成功,但也众所周知,这些模型对其投入中的小对抗扰动感到高度脆弱。即使在普遍培训的情况下,它们在扰动输入(鲁棒泛化)上的性能也会比良性输入(标准概括)的最佳可达到的性能更糟糕。因此,必须了解如何从根本上影响稳健性的情况下如何影响鲁棒性。在本文中,我们将通过专注于随机特征回归模型(具有随机第一层权重的两层神经网络)来提供超分度化对鲁棒性的作用的精确表征。我们考虑一个制度,其中样本量,输入维度和参数的数量彼此成比例地生长,并且当模型发生前列地训练时,可以为鲁棒泛化误差导出渐近精确的公式。我们的发达理论揭示了过分统计化对鲁棒性的非竞争效果,表明对于普遍训练的随机特征模型,高度公正化可能会损害鲁棒泛化。
translated by 谷歌翻译
图卷积网络(GCN)最近在学习图形结构数据方面取得了巨大的经验成功。为了解决由于相邻特征的递归嵌入而导致的可伸缩性问题,已经提出了图形拓扑抽样来降低训练GCN的记忆和计算成本,并且在许多经验研究中,它与没有拓扑采样的人达到了可比的测试性能。据我们所知,本文为半监督节点分类的训练(最多)三层GCN提供了图形拓扑采样的第一个理论理由。我们正式表征了图形拓扑抽样的一些足够条件,以使GCN训练导致概括误差减少。此外,我们的方法可以解决跨层的重量的非凸相互作用,这在GCN的现有理论分析中尚未探索。本文表征了图结构和拓扑抽样对概括性能和样本复杂性的影响,理论发现也通过数值实验证明了合理性。
translated by 谷歌翻译
通过梯度流优化平均平衡误差,研究了功能空间中神经网络的动态。我们认为,在underParameterized制度中,网络了解由与其特征值对应的率的神经切线内核(NTK)确定的整体运算符$ t_ {k ^ \ infty} $的特征功能。例如,对于SPENTE $ S ^ {D-1} $和旋转不变的权重分配的均匀分布式数据,$ t_ {k ^ \ infty} $的特征函数是球形谐波。我们的结果可以理解为描述interparameterized制度中的光谱偏压。证据使用“阻尼偏差”的概念,其中NTK物质对具有由于阻尼因子的发生而具有大特征值的特征的偏差。除了下公共条例的制度之外,阻尼偏差可用于跟踪过度分辨率设置中经验风险的动态,允许我们在文献中延长某些结果。我们得出结论,阻尼偏差在优化平方误差时提供了动态的简单和统一的视角。
translated by 谷歌翻译
训练神经网络的一种常见方法是将所有权重初始化为独立的高斯向量。我们观察到,通过将权重初始化为独立对,每对由两个相同的高斯向量组成,我们可以显着改善收敛分析。虽然已经研究了类似的技术来进行随机输入[Daniely,Neurips 2020],但尚未使用任意输入进行分析。使用此技术,我们展示了如何显着减少两层relu网络所需的神经元数量,均在逻辑损失的参数化设置不足的情况下,大约$ \ gamma^{ - 8} $ [Ji and telgarsky,ICLR, 2020]至$ \ gamma^{ - 2} $,其中$ \ gamma $表示带有神经切线内核的分离边距,以及在与平方损失的过度参数化设置中,从大约$ n^4 $ [song [song]和Yang,2019年]至$ n^2 $,隐含地改善了[Brand,Peng,Song和Weinstein,ITCS 2021]的近期运行时间。对于参数不足的设置,我们还证明了在先前工作时改善的新下限,并且在某些假设下是最好的。
translated by 谷歌翻译
This work studies training one-hidden-layer overparameterized ReLU networks via gradient descent in the neural tangent kernel (NTK) regime, where, differently from the previous works, the networks' biases are trainable and are initialized to some constant rather than zero. The first set of results of this work characterize the convergence of the network's gradient descent dynamics. Surprisingly, it is shown that the network after sparsification can achieve as fast convergence as the original network. The contribution over previous work is that not only the bias is allowed to be updated by gradient descent under our setting but also a finer analysis is given such that the required width to ensure the network's closeness to its NTK is improved. Secondly, the networks' generalization bound after training is provided. A width-sparsity dependence is presented which yields sparsity-dependent localized Rademacher complexity and a generalization bound matching previous analysis (up to logarithmic factors). As a by-product, if the bias initialization is chosen to be zero, the width requirement improves the previous bound for the shallow networks' generalization. Lastly, since the generalization bound has dependence on the smallest eigenvalue of the limiting NTK and the bounds from previous works yield vacuous generalization, this work further studies the least eigenvalue of the limiting NTK. Surprisingly, while it is not shown that trainable biases are necessary, trainable bias helps to identify a nice data-dependent region where a much finer analysis of the NTK's smallest eigenvalue can be conducted, which leads to a much sharper lower bound than the previously known worst-case bound and, consequently, a non-vacuous generalization bound.
translated by 谷歌翻译
物理信息的神经网络(PINN)是神经网络(NNS),它们作为神经网络本身的组成部分编码模型方程,例如部分微分方程(PDE)。如今,PINN是用于求解PDE,分数方程,积分分化方程和随机PDE的。这种新颖的方法已成为一个多任务学习框架,在该框架中,NN必须在减少PDE残差的同时拟合观察到的数据。本文对PINNS的文献进行了全面的综述:虽然该研究的主要目标是表征这些网络及其相关的优势和缺点。该综述还试图将出版物纳入更广泛的基于搭配的物理知识的神经网络,这些神经网络构成了香草·皮恩(Vanilla Pinn)以及许多其他变体,例如物理受限的神经网络(PCNN),各种HP-VPINN,变量HP-VPINN,VPINN,VPINN,变体。和保守的Pinn(CPINN)。该研究表明,大多数研究都集中在通过不同的激活功能,梯度优化技术,神经网络结构和损耗功能结构来定制PINN。尽管使用PINN的应用范围广泛,但通过证明其在某些情况下比有限元方法(FEM)等经典数值技术更可行的能力,但仍有可能的进步,最著名的是尚未解决的理论问题。
translated by 谷歌翻译
Online optimization with multiple budget constraints is challenging since the online decisions over a short time horizon are coupled together by strict inventory constraints. The existing manually-designed algorithms cannot achieve satisfactory average performance for this setting because they often need a large number of time steps for convergence and/or may violate the inventory constraints. In this paper, we propose a new machine learning (ML) assisted unrolling approach, called LAAU (Learning-Assisted Algorithm Unrolling), which unrolls the online decision pipeline and leverages an ML model for updating the Lagrangian multiplier online. For efficient training via backpropagation, we derive gradients of the decision pipeline over time. We also provide the average cost bounds for two cases when training data is available offline and collected online, respectively. Finally, we present numerical results to highlight that LAAU can outperform the existing baselines.
translated by 谷歌翻译
鉴于密集的浅色神经网络,我们专注于迭代创建,培训和组合随机选择的子网(代理函数),以训练完整模型。通过仔细分析$ i)$ Subnetworks的神经切线内核,II美元)$代理职能'梯度,以及$ iii)$我们如何对替代品函数进行采样并结合训练错误的线性收敛速度 - 内部一个错误区域 - 对于带有回归任务的Relu激活的过度参数化单隐藏层Perceptron。我们的结果意味着,对于固定的神经元选择概率,当我们增加代理模型的数量时,误差项会减少,并且随着我们增加每个所选子网的本地训练步骤的数量而增加。考虑的框架概括并提供了关于辍学培训,多样化辍学培训以及独立的子网培训的新见解;对于每种情况,我们提供相应的收敛结果,作为我们主要定理的冠状动脉。
translated by 谷歌翻译
机器学习在解决无线干扰管理问题方面取得了成功。已经培训了不同种类的深神经网络(DNN),以完成功率控制,波束成形和准入控制等关键任务。基于DNNS的干扰管理模型有两个流行的培训范式:监督学习(即,由优化算法产生的拟合标签)和无监督的学习(即,直接优化一些系统性能测量)。虽然这两种范式都在实践中广泛应用,但由于对这些方法缺乏任何理论理解,但目前尚不清楚如何系统地理解和比较他们的性能。在这项工作中,我们开展理论研究,为这两个训练范例提供了一些深入的了解。首先,我们展示了一些令人惊讶的结果,即对于一些特殊的功率控制问题,无监督的学习可以表现比监督对手更糟糕,因为它更有可能陷入一些低质量的本地解决方案。然后,我们提供了一系列理论结果,以进一步了解两种方法的性质。一般来说,我们表明,当有高质量的标签可用时,监督学习不太可能陷入解决方案,而不是无监督的对应物。此外,我们开发了一种半监督的学习方法,可以妥善整合这两个训练范例,可以有效地利用有限数量的标签来找到高质量的解决方案。为了我们的知识,这些是第一种在基于学习的无线通信系统设计中了解不同培训方法的第一组理论结果。
translated by 谷歌翻译
The fundamental learning theory behind neural networks remains largely open. What classes of functions can neural networks actually learn? Why doesn't the trained network overfit when it is overparameterized?In this work, we prove that overparameterized neural networks can learn some notable concept classes, including two and three-layer networks with fewer parameters and smooth activations. Moreover, the learning can be simply done by SGD (stochastic gradient descent) or its variants in polynomial time using polynomially many samples. The sample complexity can also be almost independent of the number of parameters in the network.On the technique side, our analysis goes beyond the so-called NTK (neural tangent kernel) linearization of neural networks in prior works. We establish a new notion of quadratic approximation of the neural network (that can be viewed as a second-order variant of NTK), and connect it to the SGD theory of escaping saddle points.
translated by 谷歌翻译
Autoencoders are a popular model in many branches of machine learning and lossy data compression. However, their fundamental limits, the performance of gradient methods and the features learnt during optimization remain poorly understood, even in the two-layer setting. In fact, earlier work has considered either linear autoencoders or specific training regimes (leading to vanishing or diverging compression rates). Our paper addresses this gap by focusing on non-linear two-layer autoencoders trained in the challenging proportional regime in which the input dimension scales linearly with the size of the representation. Our results characterize the minimizers of the population risk, and show that such minimizers are achieved by gradient methods; their structure is also unveiled, thus leading to a concise description of the features obtained via training. For the special case of a sign activation function, our analysis establishes the fundamental limits for the lossy compression of Gaussian sources via (shallow) autoencoders. Finally, while the results are proved for Gaussian data, numerical simulations on standard datasets display the universality of the theoretical predictions.
translated by 谷歌翻译
了解通过随机梯度下降(SGD)训练的神经网络的特性是深度学习理论的核心。在这项工作中,我们采取了平均场景,并考虑通过SGD培训的双层Relu网络,以实现一个非变量正则化回归问题。我们的主要结果是SGD偏向于简单的解决方案:在收敛时,Relu网络实现输入的分段线性图,以及“结”点的数量 - 即,Relu网络估计器的切线变化的点数 - 在两个连续的训练输入之间最多三个。特别地,随着网络的神经元的数量,通过梯度流的解决方案捕获SGD动力学,并且在收敛时,重量的分布方法接近相关的自由能量的独特最小化器,其具有GIBBS形式。我们的主要技术贡献在于分析了这一最小化器产生的估计器:我们表明其第二阶段在各地消失,除了代表“结”要点的一些特定地点。我们还提供了经验证据,即我们的理论预测的不同可能发生与数据点不同的位置的结。
translated by 谷歌翻译
神经体系结构搜索(NAS)促进了神经体系结构的自动发现,从而实现了图像识别的最新精度。尽管NAS取得了进展,但到目前为止,NAS对理论保证几乎没有关注。在这项工作中,我们研究了NAS在统一框架下的概括属性,从而实现(深)层跳过连接搜索和激活功能搜索。为此,我们从搜索空间(包括混合的激活功能,完全连接和残留的神经网络)的(包括)有限宽度方向上得出了神经切线核的最小特征值的下(和上)边界。由于在统一框架下的各种体系结构和激活功能的耦合,我们的分析是不平凡的。然后,我们利用特征值边界在随机梯度下降训练中建立NAS的概括误差界。重要的是,我们从理论上和实验上展示了衍生结果如何指导NAS,即使在没有培训的情况下,即使在没有培训的情况下,也可以根据我们的理论进行无训练的算法。因此,我们的数值验证阐明了NAS计算有效方法的设计。
translated by 谷歌翻译
在本文中,我们研究了使用深丽升方法(DRM)和物理信息的神经网络(Pinns)从随机样品求解椭圆局部微分方程(PDE)的深度学习技术的统计限制。为了简化问题,我们专注于原型椭圆PDE:SCHR \“odinginger方程,具有零的Dirichlet边界条件,其在量子 - 机械系统中具有广泛的应用。我们为两种方法建立了上下界,通过快速速率泛化绑定并发地改善了这个问题的上限。我们发现当前的深ritz方法是次优的,提出修改版本。我们还证明了Pinn和DRM的修改版本可以实现Minimax SoboLev空间的最佳限制。经验上,近期工作表明,根据权力法,我们提供了培训训练的深层模型精度,我们提供了计算实验,以显示对深PDE求解器的尺寸依赖权力法的类似行为。
translated by 谷歌翻译
We describe an algorithm that learns two-layer residual units using rectified linear unit (ReLU) activation: suppose the input $\mathbf{x}$ is from a distribution with support space $\mathbb{R}^d$ and the ground-truth generative model is a residual unit of this type, given by $\mathbf{y} = \boldsymbol{B}^\ast\left[\left(\boldsymbol{A}^\ast\mathbf{x}\right)^+ + \mathbf{x}\right]$, where ground-truth network parameters $\boldsymbol{A}^\ast \in \mathbb{R}^{d\times d}$ represent a full-rank matrix with nonnegative entries and $\boldsymbol{B}^\ast \in \mathbb{R}^{m\times d}$ is full-rank with $m \geq d$ and for $\boldsymbol{c} \in \mathbb{R}^d$, $[\boldsymbol{c}^{+}]_i = \max\{0, c_i\}$. We design layer-wise objectives as functionals whose analytic minimizers express the exact ground-truth network in terms of its parameters and nonlinearities. Following this objective landscape, learning residual units from finite samples can be formulated using convex optimization of a nonparametric function: for each layer, we first formulate the corresponding empirical risk minimization (ERM) as a positive semi-definite quadratic program (QP), then we show the solution space of the QP can be equivalently determined by a set of linear inequalities, which can then be efficiently solved by linear programming (LP). We further prove the strong statistical consistency of our algorithm, and demonstrate its robustness and sample efficiency through experimental results on synthetic data and a set of benchmark regression datasets.
translated by 谷歌翻译
We study distributionally robust optimization (DRO) with Sinkhorn distance -- a variant of Wasserstein distance based on entropic regularization. We provide convex programming dual reformulation for a general nominal distribution. Compared with Wasserstein DRO, it is computationally tractable for a larger class of loss functions, and its worst-case distribution is more reasonable. We propose an efficient first-order algorithm with bisection search to solve the dual reformulation. We demonstrate that our proposed algorithm finds $\delta$-optimal solution of the new DRO formulation with computation cost $\tilde{O}(\delta^{-3})$ and memory cost $\tilde{O}(\delta^{-2})$, and the computation cost further improves to $\tilde{O}(\delta^{-2})$ when the loss function is smooth. Finally, we provide various numerical examples using both synthetic and real data to demonstrate its competitive performance and light computational speed.
translated by 谷歌翻译
Gradient descent finds a global minimum in training deep neural networks despite the objective function being non-convex. The current paper proves gradient descent achieves zero training loss in polynomial time for a deep overparameterized neural network with residual connections (ResNet). Our analysis relies on the particular structure of the Gram matrix induced by the neural network architecture. This structure allows us to show the Gram matrix is stable throughout the training process and this stability implies the global optimality of the gradient descent algorithm. We further extend our analysis to deep residual convolutional neural networks and obtain a similar convergence result.
translated by 谷歌翻译
由于其出色的近似功率和泛化能力,物理知识的神经网络(PINNS)已成为求解高维局部微分方程(PDE)的流行选择。最近,基于域分解方法的扩展Pinns(Xpinns)由于其在模拟多尺度和多体问题问题及其平行化方面的有效性而引起了相当大的关注。但是,对其融合和泛化特性的理论理解仍未开发。在这项研究中,我们迈出了了解XPinns优于拼接的方式和当Xpinns差异的初步步骤。具体地,对于一般多层PinNS和Xpinn,我们首先通过PDE问题中的目标函数的复杂性提供先前的泛化,并且在优化之后通过网络的后矩阵规范结合。此外,根据我们的界限,我们分析了Xpinns改善泛化的条件。具体地,我们的理论表明,XPinn的关键构建块,即域分解,介绍了泛化的权衡。一方面,Xpinns将复杂的PDE解决方案分解为几个简单的部分,这降低了学习每个部分所需的复杂性并提高泛化。另一方面,分解导致每个子域内可用的训练数据较少,因此这种模型通常容易过度拟合,并且可能变得不那么广泛。经验上,我们选择五个PDE来显示XPinns比Pinns更好,类似于或更差,因此证明和证明我们的新理论。
translated by 谷歌翻译