基于变压器的大型模型在各种自然语言处理和计算机视觉任务中表现出卓越的性能。但是，这些模型包含大量参数，这些参数将其部署限制为现实世界应用程序。为了减少模型大小，研究人员根据权重的重要性得分修剪这些模型。但是，这种分数通常在训练过程中估计在小批次上，这会由于迷你批次采样和复杂的训练动力学而产生巨大的可变性/不确定性。结果，由于这种不确定性，可以通过常用的修剪方法来修剪一些关键权重，从而使训练不稳定并受到概括。为了解决这个问题，我们提出了Platon，该问题通过对重要性估计的上限（UCB）捕获了重要性得分的不确定性。特别是，对于较低的分数但不确定性较高的权重，柏拉图倾向于保留它们并探索其能力。我们对基于自然语言的理解，问答和图像分类的几种基于变压器的模型进行了广泛的实验，以验证柏拉图的有效性。结果表明，柏拉图在不同的稀疏度水平下显着改善。我们的代码可在https://github.com/qingruzhang/platon上公开获取。

基于变压器的语言模型应用于自然语言处理的广泛应用程序。但是，它们效率低，难以部署。近年来，已经提出了许多压缩算法来提高目标硬件上大型变压器的模型的实现效率。在这项工作中，我们通过整合体重修剪和模型蒸馏来提出一种训练稀疏预训练的变压器语言模型的新方法。这些稀疏的预训练型号可用于在维护稀疏模式的同时传输广泛的任务。我们展示了我们有三个已知的架构的方法，以创建稀疏的预训练伯特基，BERT-MAT​​RY和DISTOLBERT。我们展示了压缩稀疏的预训练模型如何培训他们的知识，以最小的精度损失将他们的知识转移到五种不同的下游自然语言任务。此外，我们展示了如何使用量化感知培训进一步将稀疏模型的重量压缩为8位精度。例如，在SQUAdv1.1上使用我们稀疏预训练的BERT频率，并量化为8位，我们为编码器达到40美元的压缩比，而不是1 \％$精度损失。据我们所知，我们的结果表明Bert-Base，Bert-Light和Distilbert的最佳压缩至准确率。

修剪是稀疏深神经网络的任务，最近受到了越来越多的关注。尽管最先进的修剪方法提取了高度稀疏的模型，但它们忽略了两个主要挑战：（1）寻找这些稀疏模型的过程通常非常昂贵； （2）非结构化的修剪在GPU记忆，训练时间或碳排放方面没有提供好处。我们提出了通过梯度流量保存（早期CROP）提出的早期压缩，该压缩在训练挑战（1）的培训（1）中有效提取最先进的稀疏模型，并且可以以结构化的方式应用来应对挑战（2）。这使我们能够在商品GPU上训练稀疏的网络，该商品GPU的密集版本太大，从而节省了成本并减少了硬件要求。我们从经验上表明，早期杂交的表现优于许多任务（包括分类，回归）和域（包括计算机视觉，自然语言处理和增强学习）的丰富基线。早期杂交导致准确性与密集训练相当，同时超过修剪基线。

We revisit the performance of the classic gradual magnitude pruning (GMP) baseline for large language models, focusing on the classic BERT benchmark on various popular tasks. Despite existing evidence in the literature that GMP performs poorly, we show that a simple and general variant, which we call GMP*, can match and sometimes outperform more complex state-of-the-art methods. Our results provide a simple yet strong baseline for future work, highlight the importance of parameter tuning for baselines, and even improve the performance of the state-of-the-art second-order pruning method in this setting.

Network pruning is widely used for reducing the heavy inference cost of deep models in low-resource settings. A typical pruning algorithm is a three-stage pipeline, i.e., training (a large model), pruning and fine-tuning. During pruning, according to a certain criterion, redundant weights are pruned and important weights are kept to best preserve the accuracy. In this work, we make several surprising observations which contradict common beliefs. For all state-of-the-art structured pruning algorithms we examined, fine-tuning a pruned model only gives comparable or worse performance than training that model with randomly initialized weights. For pruning algorithms which assume a predefined target network architecture, one can get rid of the full pipeline and directly train the target network from scratch. Our observations are consistent for multiple network architectures, datasets, and tasks, which imply that: 1) training a large, over-parameterized model is often not necessary to obtain an efficient final model, 2) learned "important" weights of the large model are typically not useful for the small pruned model, 3) the pruned architecture itself, rather than a set of inherited "important" weights, is more crucial to the efficiency in the final model, which suggests that in some cases pruning can be useful as an architecture search paradigm. Our results suggest the need for more careful baseline evaluations in future research on structured pruning methods. We also compare with the "Lottery Ticket Hypothesis" (Frankle & Carbin, 2019), and find that with optimal learning rate, the "winning ticket" initialization as used in Frankle & Carbin (2019) does not bring improvement over random initialization. * Equal contribution. † Work done while visiting UC Berkeley.

预先接受的语言模型（PLMS）在预训练和微调范式下，在各种自然语言处理（NLP）任务中取得了巨大成功。具有大量参数，PLMS是计算密集型和资源饥饿的。因此，已经引入了模型修剪来压缩大规模的PLM。然而，大多数先前的方法只考虑对下游任务的任务特定知识，但忽略了修剪期间的基本任务无关知识，这可能导致灾难性的遗忘问题并导致普遍性较差。为了在我们的修剪模型中维护任务不可行的特定知识，我们提出了在预训练和微调范式下的对比修剪（盖子）。它设计为一​​般框架，与结构化和非结构化修剪兼容。统一的对比学习，CAP使修剪模型能够从预训练的模型中学到任务无关的知识，以及特定于任务知识的微调模型。此外，为了更好地保留修剪模型的性能，快照（即，每个修剪迭代的中间模型）也是修剪的有效监督。我们广泛的实验表明，采用盖子一致地产生显着的改善，特别是在极高的稀疏性方案中。只有3％的型号参数保留（即97％的稀疏性），CAP成功达到了QQP和MNLI任务的原始BERT性能的99.2％和96.3％。此外，我们的探测实验表明，CAP修剪的模型趋于达到更好的泛化能力。

深度神经网络（DNN）在解决许多真实问题方面都有效。较大的DNN模型通常表现出更好的质量（例如，精度，精度），但它们的过度计算会导致长期推理时间。模型稀疏可以降低计算和内存成本，同时保持模型质量。大多数现有的稀疏算法是单向移除的重量，而其他人则随机或贪婪地探索每层进行修剪的小权重子集。这些算法的局限性降低了可实现的稀疏性水平。此外，许多算法仍然需要预先训练的密集模型，因此遭受大的内存占地面积。在本文中，我们提出了一种新颖的预定生长和修剪（间隙）方法，而无需预先培训密集模型。它通过反复生长一个层次的层来解决以前的作品的缺点，然后在一些训练后修剪回到稀疏。实验表明，使用所提出的方法修剪模型匹配或击败高度优化的密集模型的质量，在各种任务中以80％的稀疏度，例如图像分类，客观检测，3D对象分段和翻译。它们还优于模型稀疏的其他最先进的（SOTA）方法。作为一个例子，通过间隙获得的90％不均匀的稀疏resnet-50模型在想象中实现了77.9％的前1个精度，提高了先前的SOTA结果1.5％。所有代码将公开发布。

网络修剪是一种广泛使用的技术，用于有效地压缩深神经网络，几乎没有在推理期间在性能下降低。迭代幅度修剪（IMP）是由几种迭代训练和修剪步骤组成的网络修剪的最熟悉的方法之一，其中在修剪后丢失了大量网络的性能，然后在随后的再培训阶段中恢复。虽然常用为基准参考，但经常认为a）通过不将稀疏纳入训练阶段来达到次优状态，b）其全球选择标准未能正确地确定最佳层面修剪速率和c）其迭代性质使它变得缓慢和不竞争。根据最近提出的再培训技术，我们通过严格和一致的实验来调查这些索赔，我们将Impr到培训期间的训练算法进行比较，评估其选择标准的建议修改，并研究实际需要的迭代次数和总培训时间。我们发现IMP与SLR进行再培训，可以优于最先进的修剪期间，没有或仅具有很少的计算开销，即全局幅度选择标准在很大程度上具有更复杂的方法，并且只有几个刷新时期在实践中需要达到大部分稀疏性与IMP的诽谤 - 与性能权衡。我们的目标既可以证明基本的进攻已经可以提供最先进的修剪结果，甚至优于更加复杂或大量参数化方法，也可以为未来的研究建立更加现实但易于可实现的基线。

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 * .

The rectified linear unit (ReLU) is a highly successful activation function in neural networks as it allows networks to easily obtain sparse representations, which reduces overfitting in overparameterized networks. However, in network pruning, we find that the sparsity introduced by ReLU, which we quantify by a term called dynamic dead neuron rate (DNR), is not beneficial for the pruned network. Interestingly, the more the network is pruned, the smaller the dynamic DNR becomes during optimization. This motivates us to propose a method to explicitly reduce the dynamic DNR for the pruned network, i.e., de-sparsify the network. We refer to our method as Activating-while-Pruning (AP). We note that AP does not function as a stand-alone method, as it does not evaluate the importance of weights. Instead, it works in tandem with existing pruning methods and aims to improve their performance by selective activation of nodes to reduce the dynamic DNR. We conduct extensive experiments using popular networks (e.g., ResNet, VGG) via two classical and three state-of-the-art pruning methods. The experimental results on public datasets (e.g., CIFAR-10/100) suggest that AP works well with existing pruning methods and improves the performance by 3% - 4%. For larger scale datasets (e.g., ImageNet) and state-of-the-art networks (e.g., vision transformer), we observe an improvement of 2% - 3% with AP as opposed to without. Lastly, we conduct an ablation study to examine the effectiveness of the components comprising AP.

有效地近似损失函数的局部曲率信息是用于深神经网络的优化和压缩的关键工具。然而，大多数现有方法近似二阶信息具有高计算或存储成本，这可以限制其实用性。在这项工作中，我们调查矩阵，用于估计逆象征的矢量产品（IHVPS）的矩阵线性时间方法，因为当Hessian可以近似为乘语 - 一个矩阵的总和时，如Hessian的经典近似由经验丰富的Fisher矩阵。我们提出了两个新的算法作为称为M-FAC的框架的一部分：第一个算法朝着网络压缩量身定制，如果Hessian给出了M $等级的总和，则可以计算Dimension $ D $的IHVP。 ，使用$ O（DM ^ 2）$预压制，$ O（DM）$代价计算IHVP，并查询逆Hessian的任何单个元素的费用$ O（m）$。第二算法针对优化设置，我们希望在反向Hessian之间计算产品，估计在优化步骤的滑动窗口和给定梯度方向上，根据预先说明的SGD所需的梯度方向。我们为计算IHVP和OHVP和O（DM + M ^ 3）$ of $ o（dm + m ^ 2）$提供算法，以便从滑动窗口添加或删除任何渐变。这两种算法产生最先进的结果，用于网络修剪和相对于现有二阶方法的计算开销的优化。在[9]和[17]可用实现。

由于稀疏神经网络通常包含许多零权重，因此可以在不降低网络性能的情况下潜在地消除这些不必要的网络连接。因此，设计良好的稀疏神经网络具有显着降低拖鞋和计算资源的潜力。在这项工作中，我们提出了一种新的自动修剪方法 - 稀疏连接学习（SCL）。具体地，重量被重新参数化为可培训权重变量和二进制掩模的元素方向乘法。因此，由二进制掩模完全描述网络连接，其由单位步进函数调制。理论上，从理论上证明了使用直通估计器（STE）进行网络修剪的基本原理。这一原则是STE的代理梯度应该是积极的，确保掩模变量在其最小值处收敛。在找到泄漏的Relu后，SoftPlus和Identity Stes可以满足这个原理，我们建议采用SCL的身份STE以进行离散面膜松弛。我们发现不同特征的面具梯度非常不平衡，因此，我们建议将每个特征的掩模梯度标准化以优化掩码变量训练。为了自动训练稀疏掩码，我们将网络连接总数作为我们的客观函数中的正则化术语。由于SCL不需要由网络层设计人员定义的修剪标准或超级参数，因此在更大的假设空间中探讨了网络，以实现最佳性能的优化稀疏连接。 SCL克服了现有自动修剪方法的局限性。实验结果表明，SCL可以自动学习并选择各种基线网络结构的重要网络连接。 SCL培训的深度学习模型以稀疏性，精度和减少脚波特的SOTA人类设计和自动修剪方法训练。

网络修剪是一种有效的方法，可以通过可接受的性能妥协降低网络复杂性。现有研究通过耗时的重量调谐或具有扩展宽度的网络的复杂搜索来实现神经网络的稀疏性，这极大地限制了网络修剪的应用。在本文中，我们表明，在没有权重调谐的情况下，高性能和稀疏的子网被称为“彩票奖线”，存在于具有膨胀宽度的预先训练的模型中。例如，我们获得了一个只有10％参数的彩票奖金，仍然达到了原始密度Vggnet-19的性能，而无需对CiFar-10的预先训练的重量进行任何修改。此外，我们观察到，来自许多现有修剪标准的稀疏面具与我们的彩票累积的搜索掩码具有高重叠，其中，基于幅度的修剪导致与我们的最相似的掩模。根据这种洞察力，我们使用基于幅度的修剪初始化我们的稀疏掩模，导致彩票累积搜索至少3倍降低，同时实现了可比或更好的性能。具体而言，我们的幅度基彩票奖学金在Reset-50中除去90％的重量，而在ImageNet上仅使用10个搜索时期可以轻松获得超过70％的前1个精度。我们的代码可在https://github.com/zyxxmu/lottery-jackpots获得。

在过去的十年中，修剪神经网络已经流行，当时证明可以安全地从现代神经网络中安全地删除大量权重，而不会损害准确性。从那时起，已经提出了许多修剪方法，每种方法都比以前更好。如今，许多最先进的技术（SOTA）技术依赖于使用重要性得分的复杂修剪方法，通过反向传播获得反馈或在其他等方面获得基于启发式的修剪规则。我们质疑这种引入复杂性的模式，以获得更好的修剪结果。我们对这些SOTA技术基准针对全球幅度修剪（全球MP）（一个天真的修剪基线），以评估是否确实需要复杂性来实现更高的性能。全球MP按其幅度顺序排列权重，并修理最小的权重。因此，它以香草形式是最简单的修剪技术之一。令人惊讶的是，我们发现香草全球MP的表现优于所有其他SOTA技术，并取得了新的SOTA结果。它还可以在拖叉稀疏方面取得良好的性能，当以逐渐修剪的方式进行修剪时，我们发现这是增强的。我们还发现，全球MP在具有卓越性能的任务，数据集和模型之间可以推广。此外，许多修剪算法以高稀疏速率遇到的一个常见问题，即可以通过设置要保留在每层中的最小权重阈值来轻松固定在全球MP中。最后，与许多其他SOTA技术不同，全球MP不需要任何其他特定算法的超参数，并且非常简单地调整和实施。我们在各种模型（WRN-28-8，Resnet-32，Resnet-50，Mobilenet-V1和FastGrnn）和多个数据集（CIFAR-10，Imagenet和HAR-2）上展示了我们的发现。代码可在https://github.com/manasgupta-1/globalmp上找到。

关于稀疏神经网络训练（稀疏训练）的最新研究表明，通过从头开始训练本质上稀疏的神经网络可以实现绩效和效率之间的令人信服的权衡。现有的稀疏训练方法通常努力在一次跑步中找到最佳的稀疏子网，而无需涉及任何昂贵的密集或预训练步骤。例如，作为最突出的方向之一，动态稀疏训练（DST）能够通过在训练过程中迭代发展稀疏拓扑来实现竞争性训练的竞争性能。在本文中，我们认为最好分配有限的资源来创建多个低损失的稀疏子网并将其超级置于更强的基因，而不是完全分配所有资源以找到单个子网络。为了实现这一目标，需要两个Desiderata：（1）在一个培训过程中有效生产许多低损失的子网，即所谓的廉价门票，仅限于用于密集培训的标准培训时间； （2）将这些廉价的门票有效地超级为一个更强的子网，而无需超越约束参数预算。为了证实我们的猜想，我们提出了一种新颖的稀疏训练方法，称为\ textbf {sup-tickets}，可以在单个稀疏到较小的训练过程中同时满足上述两个desiderata。在CIFAR-10/100和Imagenet上的各种现代体系结构中，我们表明，SUP-Tickets与现有的稀疏训练方法无缝集成，并显示出一致的性能提高。

Neural network pruning-the task of reducing the size of a network by removing parameters-has been the subject of a great deal of work in recent years. We provide a meta-analysis of the literature, including an overview of approaches to pruning and consistent findings in the literature. After aggregating results across 81 papers and pruning hundreds of models in controlled conditions, our clearest finding is that the community suffers from a lack of standardized benchmarks and metrics. This deficiency is substantial enough that it is hard to compare pruning techniques to one another or determine how much progress the field has made over the past three decades. To address this situation, we identify issues with current practices, suggest concrete remedies, and introduce ShrinkBench, an open-source framework to facilitate standardized evaluations of pruning methods. We use ShrinkBench to compare various pruning techniques and show that its comprehensive evaluation can prevent common pitfalls when comparing pruning methods.

The importance of learning rate (LR) schedules on network pruning has been observed in a few recent works. As an example, Frankle and Carbin (2019) highlighted that winning tickets (i.e., accuracy preserving subnetworks) can not be found without applying a LR warmup schedule and Renda, Frankle and Carbin (2020) demonstrated that rewinding the LR to its initial state at the end of each pruning cycle improves performance. In this paper, we go one step further by first providing a theoretical justification for the surprising effect of LR schedules. Next, we propose a LR schedule for network pruning called SILO, which stands for S-shaped Improved Learning rate Optimization. The advantages of SILO over existing state-of-the-art (SOTA) LR schedules are two-fold: (i) SILO has a strong theoretical motivation and dynamically adjusts the LR during pruning to improve generalization. Specifically, SILO increases the LR upper bound (max_lr) in an S-shape. This leads to an improvement of 2% - 4% in extensive experiments with various types of networks (e.g., Vision Transformers, ResNet) on popular datasets such as ImageNet, CIFAR-10/100. (ii) In addition to the strong theoretical motivation, SILO is empirically optimal in the sense of matching an Oracle, which exhaustively searches for the optimal value of max_lr via grid search. We find that SILO is able to precisely adjust the value of max_lr to be within the Oracle optimized interval, resulting in performance competitive with the Oracle with significantly lower complexity.

Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching accuracy comparable to the original models. However, these tickets are proved to be notrobust to adversarial examples, and even worse than their PLM counterparts. To address this problem, we propose a novel method based on learning binary weight masks to identify robust tickets hidden in the original PLMs. Since the loss is not differentiable for the binary mask, we assign the hard concrete distribution to the masks and encourage their sparsity using a smoothing approximation of L0 regularization.Furthermore, we design an adversarial loss objective to guide the search for robust tickets and ensure that the tickets perform well bothin accuracy and robustness. Experimental results show the significant improvement of the proposed method over previous work on adversarial robustness evaluation.

This paper proposed a Soft Filter Pruning (SFP) method to accelerate the inference procedure of deep Convolutional Neural Networks (CNNs). Specifically, the proposed SFP enables the pruned filters to be updated when training the model after pruning. SFP has two advantages over previous works: (1) Larger model capacity. Updating previously pruned filters provides our approach with larger optimization space than fixing the filters to zero. Therefore, the network trained by our method has a larger model capacity to learn from the training data. (2) Less dependence on the pretrained model. Large capacity enables SFP to train from scratch and prune the model simultaneously. In contrast, previous filter pruning methods should be conducted on the basis of the pre-trained model to guarantee their performance. Empirically, SFP from scratch outperforms the previous filter pruning methods. Moreover, our approach has been demonstrated effective for many advanced CNN architectures. Notably, on ILSCRC-2012, SFP reduces more than 42% FLOPs on ResNet-101 with even 0.2% top-5 accuracy improvement, which has advanced the state-of-the-art. Code is publicly available on GitHub: https://github.com/he-y/softfilter-pruning

Most existing pruning works are resource-intensive, requiring retraining or fine-tuning of the pruned models for accuracy. We propose a retraining-free pruning method based on hyperspherical learning and loss penalty terms. The proposed loss penalty term pushes some of the model weights far from zero, while the rest weight values are pushed near zero and can be safely pruned with no need for retraining and a negligible accuracy drop. In addition, our proposed method can instantly recover the accuracy of a pruned model by replacing the pruned values with their mean value. Our method obtains state-of-the-art results in retraining-free pruning and is evaluated on ResNet-18/50 and MobileNetV2 with ImageNet dataset. One can easily get a 50\% pruned ResNet18 model with a 0.47\% accuracy drop. With fine-tuning, the experiment results show that our method can significantly boost the accuracy of the pruned models compared with existing works. For example, the accuracy of a 70\% pruned (except the first convolutional layer) MobileNetV2 model only drops 3.5\%, much less than the 7\% $\sim$ 10\% accuracy drop with conventional methods.