我们考虑在培训深度学习模型的通信约束下分布式优化。我们提出了一种新的算法，其参数更新依赖于两个力量：常规渐变步骤，以及当前最佳性能的工人（领导者）决定的纠正方向。我们的方法以多种方式与参数平均方案EASGD不同：（i）我们的客观制定与原始优化问题相比，我们的客观制定不会改变静止点的位置; （ii）我们避免通过将彼此不同局部最小值下降的本地工人拉动的融合减速（即其参数的平均值）; （iii）我们的设计更新破坏了对称性的诅咒（被困在对称非凸景观中的透过透过透过次优溶液中的现象）; （iv）我们的方法更加沟通高效，因为它仅广播领导者而不是所有工人的参数。我们提供了对所提出的算法的批量版本的理论分析，我们称之为领导者梯度下降（LGD）及其随机变体（LSGD）。最后，我们实现了算法的异步版本，并将其扩展到多领导者设置，我们组成的工人组，每个人都由自己的本地领导者（组中最佳表现者）表示，并使用纠正措施更新每个工作人员方向由两个有吸引力的力量组成：一个到当地，一个到全球领导者（所有工人中最好的表演者）。多引导设置与当前的硬件架构良好对齐，其中形成组的本地工人位于单个计算节点内，不同的组对应于不同的节点。对于培训卷积神经网络，我们经验证明了我们的方法对最先进的基线比较。

使用多个计算节点通常可以加速在大型数据集上的深度神经网络。这种方法称为分布式训练，可以通过专门的消息传递协议，例如环形全部减少。但是，以比例运行这些协议需要可靠的高速网络，其仅在专用集群中可用。相比之下，许多现实世界应用程序，例如联合学习和基于云的分布式训练，在具有不稳定的网络带宽的不可靠的设备上运行。因此，这些应用程序仅限于使用参数服务器或基于Gossip的平均协议。在这项工作中，我们通过提出MOSHPIT全部减少的迭代平均协议来提升该限制，该协议指数地收敛于全局平均值。我们展示了我们对具有强烈理论保证的分布式优化方案的效率。该实验显示了与使用抢占从头开始训练的竞争性八卦的策略和1.5倍的加速，显示了1.3倍的Imagenet培训的加速。

我们开发了一种新方法来解决中央服务器中分布式学习问题中的通信约束。我们提出和分析了一种执行双向压缩的新算法，并仅使用uplink（从本地工人到中央服务器）压缩达到与算法相同的收敛速率。为了获得此改进，我们设计了MCM，一种算法，使下行链路压缩仅影响本地模型，而整体模型则保留。结果，与以前的工作相反，本地服务器上的梯度是在干扰模型上计算的。因此，融合证明更具挑战性，需要精确控制这种扰动。为了确保它，MCM还将模型压缩与存储机制相结合。该分析打开了新的门，例如纳入依赖工人的随机模型和部分参与。

近期在应用于培训深度神经网络和数据分析中的其他优化问题中的非凸优化的优化算法的兴趣增加，我们概述了最近对非凸优化优化算法的全球性能保证的理论结果。我们从古典参数开始，显示一般非凸面问题无法在合理的时间内有效地解决。然后，我们提供了一个问题列表，可以通过利用问题的结构来有效地找到全球最小化器，因为可能的问题。处理非凸性的另一种方法是放宽目标，从找到全局最小，以找到静止点或局部最小值。对于该设置，我们首先为确定性一阶方法的收敛速率提出了已知结果，然后是最佳随机和随机梯度方案的一般理论分析，以及随机第一阶方法的概述。之后，我们讨论了非常一般的非凸面问题，例如最小化$ \ alpha $ -weakly-are-convex功能和满足Polyak-lojasiewicz条件的功能，这仍然允许获得一阶的理论融合保证方法。然后，我们考虑更高阶和零序/衍生物的方法及其收敛速率，以获得非凸优化问题。

Mini-batch stochastic gradient descent (SGD) is state of the art in large scale distributed training. The scheme can reach a linear speedup with respect to the number of workers, but this is rarely seen in practice as the scheme often suffers from large network delays and bandwidth limits. To overcome this communication bottleneck recent works propose to reduce the communication frequency. An algorithm of this type is local SGD that runs SGD independently in parallel on different workers and averages the sequences only once in a while. This scheme shows promising results in practice, but eluded thorough theoretical analysis.We prove concise convergence rates for local SGD on convex problems and show that it converges at the same rate as mini-batch SGD in terms of number of evaluated gradients, that is, the scheme achieves linear speedup in the number of workers and mini-batch size. The number of communication rounds can be reduced up to a factor of T 1/2 -where T denotes the number of total steps-compared to mini-batch SGD. This also holds for asynchronous implementations.Local SGD can also be used for large scale training of deep learning models. The results shown here aim serving as a guideline to further explore the theoretical and practical aspects of local SGD in these applications.

在过去的几年中，各种通信压缩技术已经出现为一个不可或缺的工具，有助于缓解分布式学习中的通信瓶颈。然而，尽管{\ em偏见}压缩机经常在实践中显示出卓越的性能，但与更多的研究和理解的{\ EM无偏见}压缩机相比，非常少见。在这项工作中，我们研究了三类偏置压缩操作员，其中两个是新的，并且它们在施加到（随机）梯度下降和分布（随机）梯度下降时的性能。我们首次展示偏置压缩机可以在单个节点和分布式设置中导致线性收敛速率。我们证明了具有错误反馈机制的分布式压缩SGD方法，享受ergodic速率$ \ mathcal {o} \ left（\ delta l \ exp [ - \ frac {\ mu k} {\ delta l}] + \ frac {（c + \ delta d）} {k \ mu} \右）$，其中$ \ delta \ ge1 $是一个压缩参数，它在应用更多压缩时增长，$ l $和$ \ mu $是平滑性和强凸常数，$ C $捕获随机渐变噪声（如果在每个节点上计算完整渐变，则$ C = 0 $如果在每个节点上计算），则$ D $以最佳（$ d = 0 $ for over参数化模型）捕获渐变的方差）。此外，通过对若干合成和经验的通信梯度分布的理论研究，我们阐明了为什么和通过多少偏置压缩机优于其无偏的变体。最后，我们提出了几种具有有希望理论担保和实际表现的新型偏置压缩机。

我们考虑使用梯度下降来最大程度地减少$ f（x）= \ phi（xx^{t}）$在$ n \ times r $因件矩阵$ x $上，其中$ \ phi是一种基础平稳凸成本函数定义了$ n \ times n $矩阵。虽然只能在合理的时间内发现只有二阶固定点$ x $，但如果$ x $的排名不足，则其排名不足证明其是全球最佳的。这种认证全球最优性的方式必然需要当前迭代$ x $的搜索等级$ r $，以相对于级别$ r^{\ star} $过度参数化。不幸的是，过度参数显着减慢了梯度下降的收敛性，从$ r = r = r = r^{\ star} $的线性速率到$ r> r> r> r> r^{\ star} $，即使$ \ phi $是$ \ phi $强烈凸。在本文中，我们提出了一项廉价的预处理，该预处理恢复了过度参数化的情况下梯度下降回到线性的收敛速率，同时也使在全局最小化器$ x^{\ star} $中可能不良条件变得不可知。

Training large neural networks requires distributing learning across multiple workers, where the cost of communicating gradients can be a significant bottleneck. SIGNSGD alleviates this problem by transmitting just the sign of each minibatch stochastic gradient. We prove that it can get the best of both worlds: compressed gradients and SGD-level convergence rate. The relative 1 / 2 geometry of gradients, noise and curvature informs whether SIGNSGD or SGD is theoretically better suited to a particular problem. On the practical side we find that the momentum counterpart of SIGNSGD is able to match the accuracy and convergence speed of ADAM on deep Imagenet models. We extend our theory to the distributed setting, where the parameter server uses majority vote to aggregate gradient signs from each worker enabling 1-bit compression of worker-server communication in both directions. Using a theorem by Gauss (1823) we prove that majority vote can achieve the same reduction in variance as full precision distributed SGD. Thus, there is great promise for sign-based optimisation schemes to achieve fast communication and fast convergence. Code to reproduce experiments is to be found at https://github.com/jxbz/signSGD.

许多深度学习领域都受益于使用越来越大的神经网络接受公共数据训练的培训，就像预先训练的NLP和计算机视觉模型一样。培训此类模型需要大量的计算资源（例如，HPC群集），而小型研究小组和独立研究人员则无法使用。解决问题的一种方法是，几个较小的小组将其计算资源汇总在一起并训练一种使所有参与者受益的模型。不幸的是，在这种情况下，任何参与者都可以通过故意或错误地发送错误的更新来危害整个培训。在此类同龄人的情况下进行培训需要具有拜占庭公差的专门分布式培训算法。这些算法通常通过引入冗余通信或通过受信任的服务器传递所有更新来牺牲效率，从而使它们无法应用于大规模深度学习，在该大规模深度学习中，模型可以具有数十亿个参数。在这项工作中，我们提出了一种新的协议，用于强调沟通效率的安全（容忍）分散培训。

Federated learning is a distributed framework according to which a model is trained over a set of devices, while keeping data localized. This framework faces several systemsoriented challenges which include (i) communication bottleneck since a large number of devices upload their local updates to a parameter server, and (ii) scalability as the federated network consists of millions of devices. Due to these systems challenges as well as issues related to statistical heterogeneity of data and privacy concerns, designing a provably efficient federated learning method is of significant importance yet it remains challenging. In this paper, we present FedPAQ, a communication-efficient Federated Learning method with Periodic Averaging and Quantization. FedPAQ relies on three key features: (1) periodic averaging where models are updated locally at devices and only periodically averaged at the server; (2) partial device participation where only a fraction of devices participate in each round of the training; and (3) quantized messagepassing where the edge nodes quantize their updates before uploading to the parameter server. These features address the communications and scalability challenges in federated learning. We also show that FedPAQ achieves near-optimal theoretical guarantees for strongly convex and non-convex loss functions and empirically demonstrate the communication-computation tradeoff provided by our method.

为了提高分布式学习的训练速度，近年来见证了人们对开发同步和异步分布式随机方差减少优化方法的极大兴趣。但是，所有现有的同步和异步分布式训练算法都遭受了收敛速度或实施复杂性的各种局限性。这激发了我们提出一种称为\ algname（\ ul {s} emi-as \ ul {yn}的算法} ent \ ul {s} earch），它利用方差减少框架的特殊结构来克服同步和异步分布式学习算法的局限性，同时保留其显着特征。我们考虑分布式和共享内存体系结构下的\ algname的两个实现。我们表明我们的\ algname算法具有\（o（\ sqrt {n} \ epsilon^{ - 2}（ - 2}（\ delta+1）+n）\）\）和\（o（\ sqrt {n} {n} 2}（\ delta+1）d+n）\）用于实现\（\ epsilon \）的计算复杂性 - 分布式和共享内存体系结构分别在非convex学习中的固定点，其中\（n \）表示培训样本的总数和\（\ delta \）表示工人的最大延迟。此外，我们通过建立二次强烈凸和非convex优化的算法稳定性界限来研究\ algname的概括性能。我们进一步进行广泛的数值实验来验证我们的理论发现

In distributed training of deep neural networks, parallel minibatch SGD is widely used to speed up the training process by using multiple workers. It uses multiple workers to sample local stochastic gradient in parallel, aggregates all gradients in a single server to obtain the average, and update each worker's local model using a SGD update with the averaged gradient. Ideally, parallel mini-batch SGD can achieve a linear speed-up of the training time (with respect to the number of workers) compared with SGD over a single worker. However, such linear scalability in practice is significantly limited by the growing demand for gradient communication as more workers are involved. Model averaging, which periodically averages individual models trained over parallel workers, is another common practice used for distributed training of deep neural networks since (Zinkevich et al. 2010) (McDonald, Hall, andMann 2010). Compared with parallel mini-batch SGD, the communication overhead of model averaging is significantly reduced. Impressively, tremendous experimental works have verified that model averaging can still achieve a good speed-up of the training time as long as the averaging interval is carefully controlled. However, it remains a mystery in theory why such a simple heuristic works so well. This paper provides a thorough and rigorous theoretical study on why model averaging can work as well as parallel mini-batch SGD with significantly less communication overhead.

最近，随机梯度下降（SGD）及其变体已成为机器学习（ML）问题大规模优化的主要方法。已经提出了各种策略来调整步骤尺寸，从自适应步骤大小到启发式方法，以更改每次迭代中的步骤大小。此外，动力已被广泛用于ML任务以加速训练过程。然而，我们对它们的理论理解存在差距。在这项工作中，我们开始通过为一些启发式优化方法提供正式保证并提出改进的算法来缩小这一差距。首先，我们分析了凸面和非凸口设置的Adagrad（延迟Adagrad）步骤大小的广义版本，这表明这些步骤尺寸允许算法自动适应随机梯度的噪声水平。我们首次显示延迟Adagrad的足够条件，以确保梯度几乎融合到零。此外，我们对延迟的Adagrad及其在非凸面设置中的动量变体进行了高概率分析。其次，我们用指数级和余弦的步骤分析了SGD，在经验上取得了成功，但缺乏理论支持。我们在平滑和非凸的设置中为它们提供了最初的收敛保证，有或没有polyak-{\ l} ojasiewicz（pl）条件。我们还显示了它们在PL条件下适应噪声的良好特性。第三，我们研究动量方法的最后迭代。我们证明了SGD的最后一个迭代的凸设置中的第一个下限，并以恒定的动量。此外，我们研究了一类跟随基于领先的领导者的动量算法，并随着动量和收缩的更新而增加。我们表明，他们的最后一个迭代具有最佳的收敛性，用于无约束的凸随机优化问题。

在机器学习模型的数据并行优化中，工人协作以改善对模型的估计：更准确的梯度使他们可以使用更大的学习率并更快地优化。我们考虑所有工人从同一数据集进行采样的设置，并通过稀疏图（分散）进行通信。在这种情况下，当前的理论无法捕获现实世界行为的重要方面。首先，通信图的“光谱差距”不能预测其（深）学习中的经验表现。其次，当前的理论并不能解释合作可以比单独培训更大的学习率。实际上，它规定了较小的学习率，随着图表的变化而进一步降低，无法解释无限图中的收敛性。本文旨在在工人共享相同的数据分布时绘制出稀疏连接的分布式优化的准确图片。我们量化图形拓扑如何影响二次玩具问题中的收敛性，并为一般平滑和（强烈）凸目标提供理论结果。我们的理论与深度学习中的经验观察相匹配，并准确地描述了不同图形拓扑的相对优点。

We initiate a formal study of reproducibility in optimization. We define a quantitative measure of reproducibility of optimization procedures in the face of noisy or error-prone operations such as inexact or stochastic gradient computations or inexact initialization. We then analyze several convex optimization settings of interest such as smooth, non-smooth, and strongly-convex objective functions and establish tight bounds on the limits of reproducibility in each setting. Our analysis reveals a fundamental trade-off between computation and reproducibility: more computation is necessary (and sufficient) for better reproducibility.

In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or even exhibit Byzantine failures-arbitrary and potentially adversarial behavior. In this paper, we develop distributed learning algorithms that are provably robust against such failures, with a focus on achieving optimal statistical performance. A main result of this work is a sharp analysis of two robust distributed gradient descent algorithms based on median and trimmed mean operations, respectively. We prove statistical error rates for three kinds of population loss functions: strongly convex, nonstrongly convex, and smooth non-convex. In particular, these algorithms are shown to achieve order-optimal statistical error rates for strongly convex losses. To achieve better communication efficiency, we further propose a median-based distributed algorithm that is provably robust, and uses only one communication round. For strongly convex quadratic loss, we show that this algorithm achieves the same optimal error rate as the robust distributed gradient descent algorithms.

最近的一些实证研究表明，重要的机器学习任务，例如训练深神网络，表现出低级别的结构，其中损耗函数仅在输入空间的几个方向上差异很大。在本文中，我们利用这种低级结构来降低基于规范梯度的方法（例如梯度下降（GD））的高计算成本。我们提出的\ emph {低率梯度下降}（lrgd）算法找到了$ \ epsilon $ - approximate的固定点$ p $ - 维功能，首先要识别$ r \ r \ leq p $重要的方向，然后估算真实的方向每次迭代的$ p $维梯度仅通过计算$ r $方向来计算定向衍生物。我们确定强烈凸和非convex目标函数的LRGD的“定向甲骨文复杂性”是$ \ Mathcal {o}（r \ log（1/\ epsilon） + rp） + rp）$ and $ \ Mathcal {o}（R /\ epsilon^2 + rp）$。当$ r \ ll p $时，这些复杂性小于$ \ mathcal {o}的已知复杂性（p \ log（1/\ epsilon））$和$ \ mathcal {o}（p/\ epsilon^2） {\ gd}的$分别在强凸和非凸口设置中。因此，LRGD显着降低了基于梯度的方法的计算成本，以实现足够低级别的功能。在分析过程中，我们还正式定义和表征精确且近似级别函数的类别。

深度神经网络和其他现代机器学习模型的培训通常包括解决高维且受大规模数据约束的非凸优化问题。在这里，基于动量的随机优化算法在近年来变得尤其流行。随机性来自数据亚采样，从而降低了计算成本。此外，动量和随机性都应该有助于算法克服当地的最小化器，并希望在全球范围内融合。从理论上讲，这种随机性和动量的结合被糟糕地理解。在这项工作中，我们建议并分析具有动量的随机梯度下降的连续时间模型。该模型是一个分段确定的马尔可夫过程，它通过阻尼不足的动态系统和通过动力学系统的随机切换来代表粒子运动。在我们的分析中，我们研究了长期限制，子采样到无填充采样极限以及动量到非摩托车的限制。我们对随着时间的推移降低动量的情况特别感兴趣：直觉上，动量有助于在算法的初始阶段克服局部最小值，但禁止后来快速收敛到全球最小化器。在凸度的假设下，当降低随时间的动量时，我们显示了动力学系统与全局最小化器的收敛性，并让子采样率转移到无穷大。然后，我们提出了一个稳定的，合成的离散方案，以从我们的连续时间动力学系统中构造算法。在数值实验中，我们研究了我们在凸面和非凸测试问题中的离散方案。此外，我们训练卷积神经网络解决CIFAR-10图像分类问题。在这里，与动量相比，我们的算法与随机梯度下降相比达到了竞争性结果。

We show that parametric models trained by a stochastic gradient method (SGM) with few iterations have vanishing generalization error. We prove our results by arguing that SGM is algorithmically stable in the sense of Bousquet and Elisseeff. Our analysis only employs elementary tools from convex and continuous optimization. We derive stability bounds for both convex and non-convex optimization under standard Lipschitz and smoothness assumptions.Applying our results to the convex case, we provide new insights for why multiple epochs of stochastic gradient methods generalize well in practice. In the non-convex case, we give a new interpretation of common practices in neural networks, and formally show that popular techniques for training large deep models are indeed stability-promoting. Our findings conceptually underscore the importance of reducing training time beyond its obvious benefit.

Parallel implementations of stochastic gradient descent (SGD) have received significant research attention, thanks to its excellent scalability properties. A fundamental barrier when parallelizing SGD is the high bandwidth cost of communicating gradient updates between nodes; consequently, several lossy compresion heuristics have been proposed, by which nodes only communicate quantized gradients. Although effective in practice, these heuristics do not always converge. In this paper, we propose Quantized SGD (QSGD), a family of compression schemes with convergence guarantees and good practical performance. QSGD allows the user to smoothly trade off communication bandwidth and convergence time: nodes can adjust the number of bits sent per iteration, at the cost of possibly higher variance. We show that this trade-off is inherent, in the sense that improving it past some threshold would violate information-theoretic lower bounds. QSGD guarantees convergence for convex and non-convex objectives, under asynchrony, and can be extended to stochastic variance-reduced techniques. When applied to training deep neural networks for image classification and automated speech recognition, QSGD leads to significant reductions in end-to-end training time. For instance, on 16GPUs, we can train the ResNet-152 network to full accuracy on ImageNet 1.8× faster than the full-precision variant. time to the same target accuracy is 2.7×. Further, even computationally-heavy architectures such as Inception and ResNet can benefit from the reduction in communication: on 16GPUs, QSGD reduces the end-to-end convergence time of ResNet152 by approximately 2×. Networks trained with QSGD can converge to virtually the same accuracy as full-precision variants, and that gradient quantization may even slightly improve accuracy in some settings. Related Work. One line of related research studies the communication complexity of convex optimization. In particular, [40] studied two-processor convex minimization in the same model, provided a lower bound of Ω(n(log n + log(1/ ))) bits on the communication cost of n-dimensional convex problems, and proposed a non-stochastic algorithm for strongly convex problems, whose communication cost is within a log factor of the lower bound. By contrast, our focus is on stochastic gradient methods. Recent work [5] focused on round complexity lower bounds on the number of communication rounds necessary for convex learning.Buckwild! [10] was the first to consider the convergence guarantees of low-precision SGD. It gave upper bounds on the error probability of SGD, assuming unbiased stochastic quantization, convexity, and gradient sparsity, and showed significant speedup when solving convex problems on CPUs. QSGD refines these results by focusing on the trade-off between communication and convergence. We view quantization as an independent source of variance for SGD, which allows us to employ standard convergence results [7]. The main differences from Buckw