Deep learning architectures with a huge number of parameters are often compressed using pruning techniques to ensure computational efficiency of inference during deployment. Despite multitude of empirical advances, there is a lack of theoretical understanding of the effectiveness of different pruning methods. We inspect different pruning techniques under the statistical mechanics formulation of a teacher-student framework and derive their generalization error (GE) bounds. It has been shown that Determinantal Point Process (DPP) based node pruning method is notably superior to competing approaches when tested on real datasets. Using GE bounds in the aforementioned setup we provide theoretical guarantees for their empirical observations. Another consistent finding in literature is that sparse neural networks (edge pruned) generalize better than dense neural networks (node pruned) for a fixed number of parameters. We use our theoretical setup to prove this finding and show that even the baseline random edge pruning method performs better than the DPP node pruning method. We also validate this empirically on real datasets.
Modern deep neural networks are often too large to use in many practical scenarios. Neural network pruning is an important technique for reducing the size of such models and accelerating inference. Gibbs pruning is a novel framework for expressing and designing neural network pruning methods. Combining approaches from statistical physics and stochastic regularization methods, it can train and prune a network simultaneously in such a way that the learned weights and pruning mask are well-adapted for each other. It can be used for structured or unstructured pruning and we propose a number of spe…
Bucknell University（巴克内尔大学）；University of Utah（犹他大学）；Colby College（科尔比学院）
Pruning techniques have been successfully used in neural networks to trade accuracy for sparsity. However, the impact of network pruning is not uniform: prior work has shown that the recall for underrepresented classes in a dataset may be more negatively affected. In this work, we study such relative distortions in recall by hypothesizing an intensification effect that is inherent to the model. Namely, that pruning makes recall relatively worse for a class with recall below accuracy and, conversely, that it makes recall relatively better for a class with recall above accuracy. In addition, we …
The University of Tennessee Knoxville（田纳西大学诺克斯维尔分校）；Sun Yat-sen University（中山大学）
Convolutional neural network (CNN) pruning has become one of the most successful network compression approaches in recent years. Existing works on network pruning usually focus on removing the least important filters in the network to achieve compact architectures. In this study, we claim that identifying structural redundancy plays a more essential role than finding unimportant filters, theoretically and empirically. We first statistically model the network pruning problem in a redundancy reduction perspective and find that pruning in the layer(s) with the most structural redundancy outperfor…
The University of Tokyo（东京大学）；RIKEN（日本理化学研究所）；iPride Co., Ltd.（iPride株式会社）；NTT DATA Mathematical Systems Inc.（NTT数据数学系统公司）；NTT Data Corporation（NTT数据公司）
Compression techniques for deep neural network models are becoming very important for the efficient execution of high-performance deep learning systems on edge-computing devices. The concept of model compression is also important for analyzing the generalization error of deep learning, known as the compression-based error bound. However, there is still huge gap between a practically effective compression method and its rigorous background of statistical learning theory. To resolve this issue, we develop a new theoretical framework for model compression and propose a new pruning method called {…
International Computer Science Institute（国际计算机科学研究所）；University of California, Berkeley（加利福尼亚大学伯克利分校）；Dartmouth College（达特茅斯学院）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）
Argonne Leadership Computing Facility（阿贡领导力计算设施）；Argonne National Laboratories（阿贡国家实验室）
Bayesian neural Networks (BNNs) are a promising method of obtaining statistical uncertainties for neural network predictions but with a higher computational overhead which can limit their practical usage. This work explores the use of high performance computing with distributed training to address the challenges of training BNNs at scale. We present a performance and scalability comparison of training the VGG-16 and Resnet-18 models on a Cray-XC40 cluster. We demonstrate that network pruning can speed up inference without accuracy loss and provide an open source software package, {\it{BPrune}}…
In this paper, we present a statistical-mechanical analysis of deep learning. We elucidate some of the essential components of deep learning---pre-training by unsupervised learning and fine tuning by supervised learning. We formulate the extraction of features from the training data as a margin criterion in a high-dimensional feature-vector space. The self-organized classifier is then supplied with small amounts of labelled data, as in deep learning. Although we employ a simple single-layer perceptron model, rather than directly analyzing a multi-layer neural network, we find a nontrivial phas…
Efficient Post-Training Pruning of Large Language Models with Statistical Correction
Department of Computer Science and Engineering, Santa Clara University, Santa Clara, CA, USA（计算机科学与工程系，圣克拉拉大学）；Futurewei Technologies, Inc., USA（未来韦艾技术公司）
The plateau phenomenon, wherein the loss value stops decreasing during the process of learning, has been reported by various researchers. The phenomenon is actively inspected in the 1990s and found to be due to the fundamental hierarchical structure of neural network models. Then the phenomenon has been thought as inevitable. However, the phenomenon seldom occurs in the context of recent deep learning. There is a gap between theory and reality. In this paper, using statistical mechanical formulation, we clarified the relationship between the plateau phenomenon and the statistical property of t…
SenseTime Research（商汤科技研究院）；The University of Hong Kong（香港大学）；Sun Yat-Sen University（中山大学）；The Chinese University of Hong Kong（香港中文大学）
Channel pruning is a popular technique for compressing convolutional neural networks (CNNs), where various pruning criteria have been proposed to remove the redundant filters. From our comprehensive experiments, we found two blind spots in the study of pruning criteria: (1) Similarity: There are some strong similarities among several primary pruning criteria that are widely cited and compared. According to these criteria, the ranks of filters'Importance Score are almost identical, resulting in similar pruned structures. (2) Applicability: The filters'Importance Score measured by some pruning c…
Duke University（杜克大学）；University of Minnesota（明尼苏达大学）
We propose a new structured pruning framework for compressing Deep Neural Networks (DNNs) with skip connections, based on measuring the statistical dependency of hidden layers and predicted outputs. The dependence measure defined by the energy statistics of hidden layers serves as a model-free measure of information between the feature maps and the output of the network. The estimated dependence measure is subsequently used to prune a collection of redundant and uninformative layers. Model-freeness of our measure guarantees that no parametric assumptions on the feature map distribution are req…
Pruning-induced phases in fully-connected neural networks: the eumentia, the dementia, and the amentia
Department of Physics and Astronomy, Center for Materials Theory, Rutgers University（物理与天文学系，材料理论中心，罗格斯大学）；Center for Computational Quantum Physics, Flatiron Institute（计算量子物理中心，Flatiron研究所）
UT Health Science Center at Houston（休斯顿健康科学中心）；Texas A&M University（德克萨斯农工大学）；Carnegie Mellon University（卡内基梅隆大学）
The PC algorithm is the state-of-the-art algorithm for causal structure discovery on observational data. It can be computationally expensive in the worst case due to the conditional independence tests are performed in an exhaustive-searching manner. This makes the algorithm computationally intractable when the task contains several hundred or thousand nodes, particularly when the true underlying causal graph is dense. We propose a critical observation that the conditional set rendering two nodes independent is non-unique, and including certain redundant nodes do not sacrifice result accuracy. …
