This paper is focused on the improvement the efficiency of the sparse convolutional neural networks (CNNs) layers on graphic processing units (GPU). The Nvidia deep neural network (cuDnn) library provides the most effective implementation of deep learning (DL) algorithms for GPUs. GPUs are one of the most efficient and commonly used accelerators for deep learning computations. The modern CNN models need megabytes of coefficients and needed millions MAC operations to perform convolution. One of the most common techniques for compressing CNN models is weight pruning. There are two main types of pruning: structural (based on removing whole weight channels) and non-structural (removing individual weights). The first enables much easier acceleration, but with this type it is difficult to achieve a sparsity level and accuracy as high as that obtained with the second type. Non-structural pruning with retraining can generate a matrix-weight up to $\sim90\%$ or more of sparsity in some deep CNN models. This work shows when is worth using a direct sparse operation to speed-up the calculation of the convolution layers. The VGG-16, CNN-non-static and 1x1 layers from ResNet models were used as a benchmarks. In addition, we present the impact of using reduced precision on time efficiency.
In recent years, there has been a flurry of research in deep neural network pruning and compression. Early approaches prune weights individually. However, it is difficult to take advantage of the resulting unstructured sparsity patterns on modern hardware like GPUs. As a result, pruning strategies which impose sparsity structures in the weights have become more popular. However,these structured pruning approaches typically lead to higher losses in accuracy than unstructured pruning. In this paper, we present SparseRT, a code generator that leverage unstructured sparsity to accelerate sparse li…
In this paper, we propose embedding sparsity into the structure of deep neural networks, where model parameters can be exactly zero during training with the stochastic gradient descent. Thus, it can learn the sparsified structure and the weights of networks simultaneously. The proposed approach can learn structured as well as unstructured sparsity.
Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity
Neuromorphic Computing Lab, Intel Corporation, USA；Institute of Informatics, LMU Munich, Germany；Bernoulli Institute \& CogniGron, University of Groningen, Netherlands
Dynamic Sparsity Is Channel-Level Sparsity Learner
Eindhoven University of Technology（埃因霍温理工大学）；Clemson University（克莱姆森大学）；University of Liverpool（利物浦大学）；JD Explore Academy（京东探索研究院）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
Dynamic Sparse Training of Diagonally Sparse Networks
Department of Computer Science, University of Rochester, Rochester, NY, USA（罗切斯特大学计算机科学系）；The Institute of Optics, University of Rochester, Rochester, NY, USA（罗切斯特大学光学研究所）
Sparsity-based approaches have been popular in many applications in image processing and imaging. Compressed sensing exploits the sparsity of images in a transform domain or dictionary to improve image recovery from undersampled measurements. In the context of inverse problems in dynamic imaging, recent research has demonstrated the promise of sparsity and low-rank techniques. For example, the patches of the underlying data are modeled as sparse in an adaptive dictionary domain, and the resulting image and dictionary estimation from undersampled measurements is called dictionary-blind compress…
We rigorously evaluate three state-of-the-art techniques for inducing sparsity in deep neural networks on two large-scale learning tasks: Transformer trained on WMT 2014 English-to-German, and ResNet-50 trained on ImageNet. Across thousands of experiments, we demonstrate that complex techniques (Molchanov et al., 2017; Louizos et al., 2017b) shown to yield high compression rates on smaller datasets perform inconsistently, and that simple magnitude pruning approaches achieve comparable or better results. Additionally, we replicate the experiments performed by (Frankle & Carbin, 2018) and (Liu e…
Sparsity helps reduce the computational complexity of deep neural networks by skipping zeros. Taking advantage of sparsity is listed as a high priority in next generation DNN accelerators such as TPU. The structure of sparsity, i.e., the granularity of pruning, affects the efficiency of hardware accelerator design as well as the prediction accuracy. Coarse-grained pruning creates regular sparsity patterns, making it more amenable for hardware acceleration but more challenging to maintain the same accuracy. In this paper we quantitatively measure the trade-off between sparsity regularity and pr…
Institute of Electronics（电子研究所）；AGH-UST（AGH科技大学）；Institute of Computer Science（计算机科学研究所）
This work is focused on the pruning of some convolutional neural networks (CNNs) and improving theirs efficiency on graphic processing units (GPU) by using a direct sparse algorithm. The Nvidia deep neural network (cuDnn) library is the most effective implementations of deep learning (DL) algorithms for GPUs. GPUs are the most commonly used accelerators for deep learning computations. One of the most common techniques for improving the efficiency of CNN models is weight pruning and quantization. There are two main types of pruning: structural and non-structural. The first enables much easier a…
University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Microsoft Research（微软研究院）
Sparsity in Deep Neural Networks (DNNs) is studied extensively with the focus of maximizing prediction accuracy given an overall parameter budget. Existing methods rely on uniform or heuristic non-uniform sparsity budgets which have sub-optimal layer-wise parameter allocation resulting in a) lower prediction accuracy or b) higher inference cost (FLOPs). This work proposes Soft Threshold Reparameterization (STR), a novel use of the soft-threshold operator on DNN weights. STR smoothly induces sparsity while learning pruning thresholds thereby obtaining a non-uniform sparsity budget. Our method a…
WeBank AI Group（微众银行AI集团）；Tencent Inc.（腾讯公司）；University of California, Davis（加州大学戴维斯分校）；The Hong Kong University of Science and Technology（香港科技大学）
Dual averaging-type methods are widely used in industrial machine learning applications due to their ability to promoting solution structure (e.g., sparsity) efficiently. In this paper, we propose a novel accelerated dual-averaging primal-dual algorithm for minimizing a composite convex function. We also derive a stochastic version of the proposed method which solves empirical risk minimization, and its advantages on handling sparse data are demonstrated both theoretically and empirically.
University of California, Irvine（加州大学欧文分校）；University of California, Los Angeles（加州大学洛杉矶分校）
Deep neural nets (DNNs) compression is crucial for adaptation to mobile devices. Though many successful algorithms exist to compress naturally trained DNNs, developing efficient and stable compression algorithms for robustly trained DNNs remains widely open. In this paper, we focus on a co-design of efficient DNN compression algorithms and sparse neural architectures for robust and accurate deep learning. Such a co-design enables us to advance the goal of accommodating both sparsity and robustness. With this objective in mind, we leverage the relaxed augmented Lagrangian based algorithms to pr…
Deep neural networks achieve state-of-the-art performance in a variety of tasks by extracting a rich set of features from unstructured data, however this performance is closely tied to model size. Modern techniques for inducing sparsity and reducing model size are (1) network pruning, (2) training with a sparsity inducing penalty, and (3) training a binary mask jointly with the weights of the network. We study different sparsity inducing penalties from the perspective of Bayesian hierarchical models and present a novel penalty called Hierarchical Adaptive Lasso (HALO) which learns to adaptivel…
In portable, 3-D, or ultra-fast ultrasound (US) imaging systems, there is an increasing demand to reconstruct high quality images from limited number of data. However, the existing solutions require either hardware changes or computationally expansive algorithms. To overcome these limitations, here we propose a novel deep learning approach that interpolates the missing RF data by utilizing the sparsity of the RF data in the Fourier domain. Extensive experimental results from sub-sampled RF data from a real US system confirmed that the proposed method can effectively reduce the data rate withou…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Northeastern University（东北大学）
The lottery ticket hypothesis (LTH) has shown that dense models contain highly sparse subnetworks (i.e., winning tickets) that can be trained in isolation to match full accuracy. Despite many exciting efforts being made, there is one "commonsense" rarely challenged: a winning ticket is found by iterative magnitude pruning (IMP) and hence the resultant pruned subnetworks have only unstructured sparsity. That gap limits the appeal of winning tickets in practice, since the highly irregular sparse patterns are challenging to accelerate on hardware. Meanwhile, directly substituting structured pruni…
Pruning is a model compression method that removes redundant parameters in deep neural networks (DNNs) while maintaining accuracy. Most available filter pruning methods require complex treatments such as iterative pruning, features statistics/ranking, or additional optimization designs in the training process. In this paper, we propose a simple and effective regularization strategy from a new perspective of evolution of features, which we call feature flow regularization (FFR), for improving structured sparsity and filter pruning in DNNs. Specifically, FFR imposes controls on the gradient and …
University of Rochester（罗切斯特大学）；Arm ML Research Lab（Arm机器学习研究实验室）
Exploiting sparsity is a key technique in accelerating quantized convolutional neural network (CNN) inference on mobile devices. Prior sparse CNN accelerators largely exploit un-structured sparsity and achieve significant speedups. Due to the unbounded, largely unpredictable sparsity patterns, however, exploiting unstructured sparsity requires complicated hardware design with significant energy and area overhead, which is particularly detrimental to mobile/IoT inference scenarios where energy and area efficiency are crucial. We propose to exploit structured sparsity, more specifically, Density…
Sparsity has become one of the promising methods to compress and accelerate Deep Neural Networks (DNNs). Among different categories of sparsity, structured sparsity has gained more attention due to its efficient execution on modern accelerators. Particularly, N:M sparsity is attractive because there are already hardware accelerator architectures that can leverage certain forms of N:M structured sparsity to yield higher compute-efficiency. In this work, we focus on N:M sparsity and extensively study and evaluate various training recipes for N:M sparsity in terms of the trade-off between model a…
Tight Compression: Compressing CNN Through Fine-Grained Pruning and Weight Permutation for Efficient Implementation
ACCESS - AI Chip Center for Emerging Smart Systems（ACCESS——新兴智能系统人工智能芯片中心）；Hong Kong University of Science and Technology (HKUST)（香港科技大学）；NVIDIA Corporation（英伟达公司）
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Seoul National University College of Medicine（首尔大学医学院）；Seoul National University Bundang Hospital（首尔大学盆唐医院）
The annihilating filter-based low-rank Hankel matrix approach (ALOHA) is one of the state-of-the-art compressed sensing approaches that directly interpolates the missing k-space data using low-rank Hankel matrix completion. The success of ALOHA is due to the concise signal representation in the k-space domain thanks to the duality between structured low-rankness in the k-space domain and the image domain sparsity. Inspired by the recent mathematical discovery that links convolutional neural networks to Hankel matrix decomposition using data-driven framelet basis, here we propose a fully data-d…
SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models
Multimedia Laboratory (MMLab), The Chinese University of Hong Kong（香港中文大学多媒体实验室）；Salesforce AI Research（Salesforce 人工智能研究院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；CPII under InnoHK（InnoHK 创新香港研发平台旗下产品可靠性及系统安全研发中心）
Reducing computation cost, inference latency, and memory footprint of neural networks are frequently cited as research motivations for pruning and sparsity. However, operationalizing those benefits and understanding the end-to-end effect of algorithm design and regularization on the runtime execution is not often examined in depth. Here we apply structured and unstructured pruning to attention weights of transformer blocks of the BERT language model, while also expanding block sparse representation (BSR) operations in the TVM compiler. Integration of BSR operations enables the TVM runtime exec…
Institute of Science and Technology Austria (ISTA)（奥地利科学技术研究所）；Neural Magic Inc.（Neural Magic公司）
We show for the first time that large-scale generative pretrained transformer (GPT) family models can be pruned to at least 50% sparsity in one-shot, without any retraining, at minimal loss of accuracy. This is achieved via a new pruning method called SparseGPT, specifically designed to work efficiently and accurately on massive GPT-family models. We can execute SparseGPT on the largest available open-source models, OPT-175B and BLOOM-176B, in under 4.5 hours, and can reach 60% unstructured sparsity with negligible increase in perplexity: remarkably, more than 100 billion weights from these mo…
Motivating Next-Gen Accelerators with Flexible (N:M) Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches
Applied AI（应用人工智能）；Artificial Intelligence Research Institute（人工智能研究所）；HSE University（俄罗斯高等经济大学）；Sb AI Lab（Sb人工智能实验室）；MWS AI（MWS人工智能）；Yandex；Independent Researcher（独立研究者）
Efficient Unstructured Pruning of Mamba State-Space Models for Resource-Constrained Environments
Department of Computer Science, Iowa State University（计算机科学系，爱荷华州立大学）；Department of Civil, Construction and Environmental Engineering, Iowa State University（土木、建设与环境工程系，爱荷华州立大学）
Robert Bosch GmbH（罗伯特·博世有限公司）；University of Lübeck（吕贝克大学）
Unstructured pruning is well suited to reduce the memory footprint of convolutional neural networks (CNNs), both at training and inference time. CNNs contain parameters arranged in $K \times K$ filters. Standard unstructured pruning (SP) reduces the memory footprint of CNNs by setting filter elements to zero, thereby specifying a fixed subspace that constrains the filter. Especially if pruning is applied before or during training, this induces a strong bias. To overcome this, we introduce interspace pruning (IP), a general tool to improve existing pruning methods. It uses filters represented i…
