Pruning is one of the predominant approaches for compressing deep neural networks (DNNs). Lately, coresets (provable data summarizations) were leveraged for pruning DNNs, adding the advantage of theoretical guarantees on the trade-off between the compression rate and the approximation error. However, coresets in this domain were either data dependant or generated under restrictive assumptions on both the model's weights and inputs. In real-world scenarios, such assumptions are rarely satisfied, limiting the applicability of coresets. To this end, we suggest a novel and robust framework for computing such coresets under mild assumptions on the model's weights and without any assumption on the training data. The idea is to compute the importance of each neuron in each layer with respect to the output of the following layer. This is achieved by an elegant combination of L\{o}wner ellipsoid and Caratheodory theorem.Our method is simultaneously data-independent, applicable to various networks and datasets (due to the simplified assumptions), and theoretically supported. Experimental results show that our method outperforms existing coreset based neural pruning approaches across a wide range of networks and datasets. For example, our method achieved a $62\%$ compression rate on ResNet50 on ImageNet with $1.09\%$ drop in accuracy.

Pruning the parameters of deep neural networks has generated intense interest due to potential savings in time, memory and energy both during training and at test time. Recent works have identified, through an expensive sequence of training and pruning cycles, the existence of winning lottery tickets or sparse trainable subnetworks at initialization. This raises a foundational question: can we identify highly sparse trainable subnetworks at initialization, without ever training, or indeed without ever looking at the data? We provide an affirmative answer to this question through theory driven algorithm design. We first mathematically formulate and experimentally verify a conservation law that explains why existing gradient-based pruning algorithms at initialization suffer from layer-collapse, the premature pruning of an entire layer rendering a network untrainable. This theory also elucidates how layer-collapse can be entirely avoided, motivating a novel pruning algorithm Iterative Synaptic Flow Pruning (SynFlow). This algorithm can be interpreted as preserving the total flow of synaptic strengths through the network at initialization subject to a sparsity constraint. Notably, this algorithm makes no reference to the training data and consistently competes with or outperforms existing state-of-the-art pruning algorithms at initialization over a range of models (VGG and ResNet), datasets (CIFAR-10/100 and Tiny ImageNet), and sparsity constraints (up to 99.99 percent). Thus our data-agnostic pruning algorithm challenges the existing paradigm that, at initialization, data must be used to quantify which synapses are important.

Pruning the parameters of deep neural networks has generated intense interest due to potential savings in time, memory and energy both during training and at test time. Recent works have identified, through an expensive sequence of training and pruning cycles, the existence of winning lottery tickets or sparse trainable subnetworks at initialization. This raises a foundational question: can we identify highly sparse trainable subnetworks at initialization, without ever training, or indeed without ever looking at the data? We provide an affirmative answer to this question through theory driven algorithm design. We first mathematically formulate and experimentally verify a conservation law that explains why existing gradient-based pruning algorithms at initialization suffer from layer-collapse, the premature pruning of an entire layer rendering a network untrainable.

Weaknesses: Method: - Theorem 1 is not new, and similar results were already presented in previous work [Liang et al., 2019]. For the proof of Theorem 1, In L171, there are no bias terms that appeared in computing z_j. However, for ResNet and VGGNet they all have bias terms at each layer, so this theorem does not apply for them. For example, when the input data is very sparse and most of its dimensions are not correlated with the prediction, then you can probably prune a lot at the input layer. Therefore, I am not convinced with the motivation of data-independent pruning.

This paper introduces synaptic saliency for deep network pruning which does not require any dataset. While there is overall appreciation of the results theoretically there are some concerns about the experiments. The authors have addressed some of the issues and contingent on their addressing the concerns one can recommend acceptance.

Pruning is one of the predominant approaches for compressing deep neural networks (DNNs). Lately, coresets (provable data summarizations) were leveraged for pruning DNNs, adding the advantage of theoretical guarantees on the trade-off between the compression rate and the approximation error. However, coresets in this domain were either data dependant or generated under restrictive assumptions on both the model's weights and inputs. In real-world scenarios, such assumptions are rarely satisfied, limiting the applicability of coresets. To this end, we suggest a novel and robust framework for computing such coresets under mild assumptions on the model's weights and without any assumption on the training data.

Pruning the parameters of deep neural networks has generated intense interest due to potential savings in time, memory and energy both during training and at test time. Recent works have identified, through an expensive sequence of training and pruning cycles, the existence of winning lottery tickets or sparse trainable subnetworks at initialization. This raises a foundational question: can we identify highly sparse trainable subnetworks at initialization, without ever training, or indeed without ever looking at the data? We provide an affirmative answer to this question through theory driven algorithm design. We first mathematically formulate and experimentally verify a conservation law that explains why existing gradient-based pruning algorithms at initialization suffer from layer-collapse, the premature pruning of an entire layer rendering a network untrainable.

Neural network pruning is a popular technique used to reduce the inference costs of modern, potentially overparameterized, networks. Starting from a pre-trained network, the process is as follows: remove redundant parameters, retrain, and repeat while maintaining the same test accuracy. The result is a model that is a fraction of the size of the original with comparable predictive performance (test accuracy). Here, we reassess and evaluate whether the use of test accuracy alone in the terminating condition is sufficient to ensure that the resulting model performs well across a wide spectrum of "harder" metrics such as generalization to out-of-distribution data and resilience to noise. Across evaluations on varying architectures and data sets, we find that pruned networks effectively approximate the unpruned model, however, the prune ratio at which pruned networks achieve commensurate performance varies significantly across tasks. These results call into question the extent of \emph{genuine} overparameterization in deep learning and raise concerns about the practicability of deploying pruned networks, specifically in the context of safety-critical systems, unless they are widely evaluated beyond test accuracy to reliably predict their performance. Our code is available at https://github.com/lucaslie/torchprune.

Much of the success of deep learning has come from building larger and larger neural networks. This allows these models to perform better on various tasks, but also makes them more expensive to use. Larger models take more storage space which makes them harder to distribute. Larger models also take more time to run and can require more expensive hardware. This is especially a concern if you are productionizing a model for a real-world application.

Pruning is a popular technique for compressing a neural network: a large pre-trained network is fine-tuned while connections are successively removed. However, the value of pruning has largely evaded scrutiny. In this extended abstract, we examine residual networks obtained through Fisher-pruning and make two interesting observations. First, when time-constrained, it is better to train a simple, smaller network from scratch than prune a large network. Second, it is the architectures obtained through the pruning process --- not the learnt weights ---that prove valuable. Such architectures are powerful when trained from scratch. Furthermore, these architectures are easy to approximate without any further pruning: we can prune once and obtain a family of new, scalable network architectures for different memory requirements.