深度学习的成功归功于我们能够相对轻松地解决某些大规模的非凸优化问题。尽管非凸优化是NP硬化，但简单的算法（通常是随机梯度下降的变体）在拟合大型神经网络的实践中具有令人惊讶的有效性。我们认为，在考虑了所有可能的隐藏单元对称对称性之后，神经网络损失景观包含（几乎）一个盆地。我们介绍了三种算法以缩小一个模型的单元，以使它们与参考模型的单位保持一致。这种转换产生了一组功能等效的权重，该权重位于参考模型附近的大约凸盆地中。在实验上，我们证明了各种模型架构和数据集中的单个盆地现象，包括在CIFAR-10和CIFAR-100上独立训练的Resnet模型之间的第一个（据我们所知）的（据我们所知）的第一次演示。此外，我们确定了有趣的现象，将模型宽度和训练时间与各种模型和数据集的模式连接性有关。最后，我们讨论了单个盆地理论的缺点，包括对线性模式连接假设的反例。

In this paper we look into the conjecture of Entezari et al. (2021) which states that if the permutation invariance of neural networks is taken into account, then there is likely no loss barrier to the linear interpolation between SGD solutions. First, we observe that neuron alignment methods alone are insufficient to establish low-barrier linear connectivity between SGD solutions due to a phenomenon we call variance collapse: interpolated deep networks suffer a collapse in the variance of their activations, causing poor performance. Next, we propose REPAIR (REnormalizing Permuted Activations for Interpolation Repair) which mitigates variance collapse by rescaling the preactivations of such interpolated networks. We explore the interaction between our method and the choice of normalization layer, network width, and depth, and demonstrate that using REPAIR on top of neuron alignment methods leads to 60%-100% relative barrier reduction across a wide variety of architecture families and tasks. In particular, we report a 74% barrier reduction for ResNet50 on ImageNet and 90% barrier reduction for ResNet18 on CIFAR10.

在本文中，我们推测，如果考虑到神经网络的置换不变性，SGD解决方案可能不会在它们之间的线性插值中没有障碍。尽管这是一个大胆的猜想，但我们展示了广泛的经验尝试却没有反驳。我们进一步提供了初步的理论结果来支持我们的猜想。我们的猜想对彩票票证假设，分布式培训和合奏方法有影响。

The recent emergence of new algorithms for permuting models into functionally equivalent regions of the solution space has shed some light on the complexity of error surfaces, and some promising properties like mode connectivity. However, finding the right permutation is challenging, and current optimization techniques are not differentiable, which makes it difficult to integrate into a gradient-based optimization, and often leads to sub-optimal solutions. In this paper, we propose a Sinkhorn re-basin network with the ability to obtain the transportation plan that better suits a given objective. Unlike the current state-of-art, our method is differentiable and, therefore, easy to adapt to any task within the deep learning domain. Furthermore, we show the advantage of our re-basin method by proposing a new cost function that allows performing incremental learning by exploiting the linear mode connectivity property. The benefit of our method is compared against similar approaches from the literature, under several conditions for both optimal transport finding and linear mode connectivity. The effectiveness of our continual learning method based on re-basin is also shown for several common benchmark datasets, providing experimental results that are competitive with state-of-art results from the literature.

我们通过将其基于实现功能空间而不是参数空间的几何形状来系统地研究深度神经网络景观的方法。将分类器分组到等效类中，我们开发了一个标准化的参数化，其中所有对称性都被删除，从而导致环形拓扑。在这个空间上，我们探讨了误差景观而不是损失。这使我们能够得出有意义的概念，即最小化器的平坦度和连接它们的地球通道的概念。使用不同的优化算法，这些算法采样具有不同平坦度的最小化器，我们研究模式连接性和相对距离。测试各种最先进的体系结构和基准数据集，我们确认了平面度和泛化性能之间的相关性；我们进一步表明，在功能空间中，minima彼此更近，并且连接它们的大地测量学的屏障很小。我们还发现，通过梯度下降的变体发现的最小化器可以通过由参数空间中的两个直线组成的零误差路径连接，即带有单个弯曲的多边形链。我们观察到具有二进制权重和激活的神经网络中相似的定性结果，这为在这种情况下的连通性提供了第一个结果之一。我们的结果取决于对称性的去除，并且与对简单浅层模型进行的一些分析研究所描述的丰富现象学非常吻合。

从不同的随机初始化开始，经过随机梯度下降（SGD）训练的神经网络通常在功能上非常相似，从而提出了一个问题，即不同的SGD溶液之间是否存在有意义的差异。 Entezari等。最近猜想，尽管初始化不同，但在考虑到神经网络的置换不变性后，SGD发现的解决方案位于相同的损失谷中。具体而言，他们假设可以将SGD找到的任何两种解决方案排列，以使其参数之间的线性插值形成一条路径，而不会显着增加损失。在这里，我们使用一种简单但功能强大的算法来找到这样的排列，使我们能够获得直接的经验证据，证明该假设在完全连接的网络中是正确的。引人注目的是，我们发现在初始化时已经存在两个网络，并且平均它们随机，但适当排列的初始化的性能大大高于机会。相反，对于卷积架构，我们的证据表明该假设不存在。特别是在大型学习率制度中，SGD似乎发现了各种模式。

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。

我们研究了使用尖刺，现场依赖的随机矩阵理论研究迷你批次对深神经网络损失景观的影响。我们表明，批量黑森州的极值值的大小大于经验丰富的黑森州。我们还获得了类似的结果对Hessian的概括高斯牛顿矩阵近似。由于我们的定理，我们推导出作为批量大小的最大学习速率的分析表达式，为随机梯度下降（线性缩放）和自适应算法（例如ADAM（Square Root Scaling）提供了通知实际培训方案，例如光滑，非凸深神经网络。虽然随机梯度下降的线性缩放是在我们概括的更多限制性条件下导出的，但是适应优化者的平方根缩放规则是我们的知识，完全小说。随机二阶方法和自适应方法的百分比，我们得出了最小阻尼系数与学习率与批量尺寸的比率成比例。我们在Cifar-$ 100 $和ImageNet数据集上验证了我们的VGG / WimerEsnet架构上的索赔。根据我们对象检的调查，我们基于飞行学习率和动量学习者开发了一个随机兰齐齐竞争，这避免了对这些关键的超参数进行昂贵的多重评估的需求，并在预残留的情况下显示出良好的初步结果Cifar的architecure - $ 100 $。

在他们的损失景观方面观看神经网络模型在学习的统计力学方法方面具有悠久的历史，并且近年来它在机器学习中得到了关注。除此之外，已显示局部度量（例如损失景观的平滑度）与模型的全局性质（例如良好的泛化性能）相关联。在这里，我们对数千个神经网络模型的损失景观结构进行了详细的实证分析，系统地改变了学习任务，模型架构和/或数据数量/质量。通过考虑试图捕获损失景观的不同方面的一系列指标，我们证明了最佳的测试精度是如下：损失景观在全球连接;训练型模型的集合彼此更像;而模型会聚到局部平滑的地区。我们还表明，当模型很小或培训以较低质量数据时，可以出现全球相连的景观景观;而且，如果损失景观全球相连，则培训零损失实际上可以导致更糟糕的测试精度。我们详细的经验结果阐明了学习阶段的阶段（以及后续双重行为），基本与偶然的决定因素良好的概括决定因素，负载样和温度相同的参数在学习过程中，不同的影响对模型的损失景观的影响不同和数据，以及地方和全球度量之间的关系，近期兴趣的所有主题。

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.

Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models. Oftentimes fine-tuned models are readily available but their training data is not, due to data privacy or intellectual property concerns. This creates a barrier to fusing knowledge across individual models to yield a better single model. In this paper, we study the problem of merging individual models built on different training data sets to obtain a single model that performs well both across all data set domains and can generalize on out-of-domain data. We propose a dataless knowledge fusion method that merges models in their parameter space, guided by weights that minimize prediction differences between the merged model and the individual models. Over a battery of evaluation settings, we show that the proposed method significantly outperforms baselines such as Fisher-weighted averaging or model ensembling. Further, we find that our method is a promising alternative to multi-task learning that can preserve or sometimes improve over the individual models without access to the training data. Finally, model merging is more efficient than training a multi-task model, thus making it applicable to a wider set of scenarios.

深度学习在广泛的AI应用方面取得了有希望的结果。较大的数据集和模型一致地产生更好的性能。但是，我们一般花费更长的培训时间，以更多的计算和沟通。在本调查中，我们的目标是在模型精度和模型效率方面提供关于大规模深度学习优化的清晰草图。我们调查最常用于优化的算法，详细阐述了大批量培训中出现的泛化差距的可辩论主题，并审查了解决通信开销并减少内存足迹的SOTA策略。

Many applications require sparse neural networks due to space or inference time restrictions. There is a large body of work on training dense networks to yield sparse networks for inference, but this limits the size of the largest trainable sparse model to that of the largest trainable dense model. In this paper we introduce a method to train sparse neural networks with a fixed parameter count and a fixed computational cost throughout training, without sacrificing accuracy relative to existing dense-tosparse training methods. Our method updates the topology of the sparse network during training by using parameter magnitudes and infrequent gradient calculations. We show that this approach requires fewer floating-point operations (FLOPs) to achieve a given level of accuracy compared to prior techniques. We demonstrate state-of-the-art sparse training results on a variety of networks and datasets, including ResNet-50, MobileNets on Imagenet-2012, and RNNs on WikiText-103. Finally, we provide some insights into why allowing the topology to change during the optimization can overcome local minima encountered when the topology remains static * .

通过更好地了解多层网络的损失表面，我们可以构建更强大和准确的培训程序。最近发现，独立训练的SGD解决方案可以沿近持续训练损失的一维路径连接。在本文中，我们表明存在模式连接的单纯复合物，形成低损耗的多维歧管，连接许多独立培训的型号。灵感来自这一发现，我们展示了如何有效地建立快速合奏的单纯性复杂，表现优于准确性，校准和对数据集移位的鲁棒性的独立培训的深度集合。值得注意的是，我们的方法只需要几个训练时期来发现低损失单纯乳，从预先接受训练的解决方案开始。代码可在https://github.com/g-benton/loss-surface-simplexes中获得。

In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited. We develop a Bayesian nonparametric framework for federated learning with neural networks. Each data server is assumed to provide local neural network weights, which are modeled through our framework. We then develop an inference approach that allows us to synthesize a more expressive global network without additional supervision, data pooling and with as few as a single communication round. We then demonstrate the efficacy of our approach on federated learning problems simulated from two popular image classification datasets. 1

对称性一直是探索广泛复杂系统的基本工具。在机器学习中，在模型和数据中都探索了对称性。在本文中，我们试图将模型家族架构引起的对称性与该家族的内部数据表示的对称性联系起来。我们通过计算一组基本的对称组来做到这一点，我们称它们称为模型的\ emph {Intertwiner组}。这些中的每一个都来自模型的特定非线性层，不同的非线性导致不同的对称组。这些组以模型的权重更改模型的权重，使模型所代表的基础函数保持恒定，但模型内部数据的内部表示可能会改变。我们通过一系列实验将Intertwiner组连接到模型的数据内部表示，这些实验在具有相同体系结构的模型之间探测隐藏状态之间的相似性。我们的工作表明，网络的对称性在该网络的数据表示中传播到对称性中，从而使我们更好地了解架构如何影响学习和预测过程。最后，我们推测，对于Relu网络，交织组可能会为在隐藏层而不是任意线性组合的激活基础上集中模型可解释性探索的共同实践提供理由。

Federated learning allows edge devices to collaboratively learn a shared model while keeping the training data on device, decoupling the ability to do model training from the need to store the data in the cloud. We propose the Federated matched averaging (FedMA) algorithm designed for federated learning of modern neural network architectures e.g. convolutional neural networks (CNNs) and LSTMs. FedMA constructs the shared global model in a layer-wise manner by matching and averaging hidden elements (i.e. channels for convolution layers; hidden states for LSTM; neurons for fully connected layers) with similar feature extraction signatures. Our experiments indicate that FedMA not only outperforms popular state-of-the-art federated learning algorithms on deep CNN and LSTM architectures trained on real world datasets, but also reduces the overall communication burden. 1 * Work performed while doing an internship at IBM Research.

Neural network training relies on our ability to find "good" minimizers of highly non-convex loss functions. It is well-known that certain network architecture designs (e.g., skip connections) produce loss functions that train easier, and wellchosen training parameters (batch size, learning rate, optimizer) produce minimizers that generalize better. However, the reasons for these differences, and their effects on the underlying loss landscape, are not well understood. In this paper, we explore the structure of neural loss functions, and the effect of loss landscapes on generalization, using a range of visualization methods. First, we introduce a simple "filter normalization" method that helps us visualize loss function curvature and make meaningful side-by-side comparisons between loss functions. Then, using a variety of visualizations, we explore how network architecture affects the loss landscape, and how training parameters affect the shape of minimizers.

组合优化是运营研究和计算机科学领域的一个公认领域。直到最近，它的方法一直集中在孤立地解决问题实例，而忽略了它们通常源于实践中的相关数据分布。但是，近年来，人们对使用机器学习，尤其是图形神经网络（GNN）的兴趣激增，作为组合任务的关键构件，直接作为求解器或通过增强确切的求解器。GNN的电感偏差有效地编码了组合和关系输入，因为它们对排列和对输入稀疏性的意识的不变性。本文介绍了对这个新兴领域的最新主要进步的概念回顾，旨在优化和机器学习研究人员。

在神经网络的经验风险景观中扁平最小值的性质已经讨论了一段时间。越来越多的证据表明他们对尖锐物质具有更好的泛化能力。首先，我们讨论高斯混合分类模型，并分析显示存在贝叶斯最佳点估算器，其对应于属于宽平区域的最小值。可以通过直接在分类器（通常是独立的）或学习中使用的可分解损耗函数上应用最大平坦度算法来找到这些估计器。接下来，我们通过广泛的数值验证将分析扩展到深度学习场景。使用两种算法，熵-SGD和复制-SGD，明确地包括在优化目标中，所谓的非局部平整度措施称为本地熵，我们一直提高常见架构的泛化误差（例如Resnet，CeffectnNet）。易于计算的平坦度测量显示与测试精度明确的相关性。