We examine how recently documented, fundamental phenomena in deep learning models subject to pruning are affected by changes in the pruning procedure. Specifically, we analyze differences in the connectivity structure and learning dynamics of pruned models found through a set of common iterative pruning techniques, to …
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “structured pruning”
Speeds up training and inference by pruning entire channels before training.
problem Training and inference speed in deep neural networks.
method Structured pruning applied before training, focusing on removing entire channels and hidden units.
result 2x speedup in training and 3x speedup in inference.
Structured pruning is a popular method for compressing a neural network: given a large trained network, one alternates between removing channel connections and fine-tuning; reducing the overall width of the network. However, the efficacy of structured pruning has largely evaded scrutiny. In this paper, we examine ResNe…
BMRS offers a Bayesian approach to structured pruning of neural networks.
problem Overparameterized neural networks lead to high compute costs.
method Bayesian Model Reduction for Structured pruning (BMRS) based on two recent methods: Bayesian structured pruning with multiplicative noise and Bayesian model reduction.
result BMRS yields high compression rates and accuracy without tuning thresholds.
The state-of-art DNN structures involve high computation and great demand for memory storage which pose intensive challenge on DNN framework resources. To mitigate the challenges, weight pruning techniques has been studied. However, high accuracy solution for extreme structured pruning that combines different types of …
Model compression techniques on Deep Neural Network (DNN) have been widely acknowledged as an effective way to achieve acceleration on a variety of platforms, and DNN weight pruning is a straightforward and effective method. There are currently two mainstreams of pruning methods representing two extremes of pruning reg…
A new pruning method reduces neural network computation without retraining.
problem Efficiently reduce neural network computation while maintaining accuracy.
method Structured directional pruning via perturbation orthogonal projection.
result Achieves state-of-the-art pruned accuracy without retraining.
CupNet prunes neural nets for cup-shaped data.
problem Pruning neural networks for cup-shaped data.
method Used simulated cup drawing data to prune a neural network.
result Pruning effectively reduces network size for cup-shaped data.
i-SpaSP prunes neural networks by identifying important groups of parameters, improving pruning efficiency.
problem Pruning neural networks to reduce computational cost and improve performance.
method i-SpaSP uses sparse signal recovery principles to iteratively identify and threshold important parameter groups.
result i-SpaSP achieves strong empirical results and theoretical convergence guarantees, improving pruning efficiency.
A new pruning method improves neural network efficiency and accuracy.
problem Optimizing neural network efficiency and accuracy through pruning.
method Formulated as a Knapsack Problem, the method optimizes trade-off between neuron importance and computational cost. Channels are pruned while maintaining network structure, and fine-tuned using inner knowledge distillation from parent network.
result State-of-the-art pruning results on ImageNet, CIFAR-10, and CIFAR-100.
In this paper, we propose a novel progressive parameter pruning method for Convolutional Neural Network acceleration, named Structured Probabilistic Pruning (SPP), which effectively prunes weights of convolutional layers in a probabilistic manner. Unlike existing deterministic pruning approaches, where unimportant weig…
Large deep neural network (DNN) models pose the key challenge to energy efficiency due to the significantly higher energy consumption of off-chip DRAM accesses than arithmetic or SRAM operations. It motivates the intensive research on model compression with two main approaches. Weight pruning leverages the redundancy i…
Pruning is a standard technique for removing unnecessary structure from a neural network to reduce its storage footprint, computational demands, or energy consumption. Pruning can reduce the parameter-counts of many state-of-the-art neural networks by an order of magnitude without compromising accuracy, meaning these n…
Structured weight pruning is a representative model compression technique of DNNs to reduce the storage and computation requirements and accelerate inference. An automatic hyperparameter determination process is necessary due to the large number of flexible hyperparameters. This work proposes AutoCompress, an automatic…
New pruning method for sparse additive models speeds up causal structure learning.
problem Efficiently prune spurious edges from fully-connected DAG induced by estimated topological order.
method Sparse additive models combined with randomized tree embedding and group-wise sparse regression.
result Significantly faster than existing pruning methods while maintaining comparable accuracy.
Pruning method removes less important features in linear models.
problem Removing less important features in linear models trained by gradient flow.
method Iterative Magnitude Pruning (IMP) applied to linear models trained by gradient flow.
result IMP prunes features with smallest projection onto the data.
Large language models have recently achieved state of the art performance across a wide variety of natural language tasks. Meanwhile, the size of these models and their latency have significantly increased, which makes their usage costly, and raises an interesting question: do language models need to be large? We study…
Optimization-based pruning eliminates backpropagation for large language models.
problem Suboptimal pruning performance due to heuristic metrics.
method Optimization of Bernoulli distribution to learn pruning masks without backpropagation.
result Efficient pruning of large language models with improved performance.
A model predicts how hyperparameters affect pruning performance.
problem Predicting the impact of hyperparameters on pruning performance.
method Phenomenological model using temperature-like and load-like parameters.
result A sharp transition phenomenon in pruning performance.
ResRep prunes CNNs without losing accuracy by separating remembering and forgetting.
problem Pruning CNNs to reduce FLOPs without sacrificing accuracy.
method Decoupling remembering and forgetting in CNNs, using SGD for remembering and a novel update rule for forgetting.
result Achieved lossless pruning with high compression ratio (76.15% accuracy on ImageNet with 45% FLOPs reduction).
Gibbs pruning optimizes neural networks by combining physics and regularization.
problem Large neural networks are impractical for many applications.
method Combines statistical physics and stochastic regularization to train and prune networks simultaneously.
result Gibbs pruning achieves state-of-the-art performance on ResNet-56.
The study reveals flaws in pruning criteria and proposes a new assumption for better filter selection.
problem Flaws in existing pruning criteria for CNNs.
method Empirical experiments and Convolutional Weight Distribution Assumption.
result The Convolutional Weight Distribution Assumption improves filter selection in pruning.
A new method prunes neural networks faster and more efficiently.
problem Reducing training time and memory usage for neural networks.
method Set-based Task-Adaptive Meta Pruning (STAMP) that meta-learns a pruning mask.
result Significantly improved compression rates and faster training speed.
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 weigh…
Reducing the test time resource requirements of a neural network while preserving test accuracy is crucial for running inference on resource-constrained devices. To achieve this goal, we introduce a novel network reparameterization based on the Kronecker-factored eigenbasis (KFE), and then apply Hessian-based structure…
New pruning method captures global correlations for efficient neural network inference.
problem Efficiently pruning neural networks for faster inference and reduced memory usage.
method Second-order structured pruning (SOSP-H) with innovative saliency-based approaches.
result SOSP-H scales to large-scale vision tasks and improves accuracy without compromising efficiency.
DJPQ optimizes neural network pruning and quantization for hardware efficiency.
problem Efficiently compress neural networks for hardware inference.
method Joint gradient-based optimization of pruning and quantization into a differentiable loss function.
result Significant reduction in Bit-Operations (BOPs) with minimal accuracy loss.
Deep neural networks have dramatically achieved great success on a variety of challenging tasks. However, most successful DNNs have an extremely complex structure, leading to extensive research on model compression.As a significant area of progress in model compression, traditional gradual pruning approaches involve an…
Accelerating DNN execution on various resource-limited computing platforms has been a long-standing problem. Prior works utilize l1-based group lasso or dynamic regularization such as ADMM to perform structured pruning on DNN models to leverage the parallel computing architectures. However, both of the pruning dimensio…
The sophisticated structure of Convolutional Neural Network (CNN) allows for outstanding performance, but at the cost of intensive computation. As significant redundancies inevitably present in such a structure, many works have been proposed to prune the convolutional filters for computation cost reduction. Although ex…
A new method quantifies feature-map discriminativeness for efficient pruning of deep neural networks.
problem Efficiently pruning deep neural networks to reduce computation while maintaining accuracy.
method Presented a novel mathematical formulation (Discriminant Information, DI) to quantify feature-map discriminativeness, enabling efficient pruning and intra-layer mixed precision quantization.
result Our pruned ResNet50 achieves 44% FLOPs reduction without any Top-1 accuracy loss.
This paper studies a theoretical pruning method for RNNs to reduce computational costs.
problem High computational costs in recurrent neural networks (RNNs).
method Spectral pruning inspired approach for RNNs.
result Generalization error bounds for compressed RNNs are provided.
Paper proposes efficient network pruning method for deep neural networks.
problem High computational and memory cost of deep neural networks.
method Annealing and direct sparsity control for channel-level pruning.
result Proposed method achieves better or competitive performance compared to other methods.
Safe Pattern Pruning reduces pattern explosion in predictive pattern mining.
problem Exponential growth of patterns in structured data.
method Safe Pattern Pruning (SPP) method.
result Effective model building in practical data analysis.
This work explores the importance of model weights and Hessian bias in pruning.
problem Understanding the relative importance of model weights for efficient pruning.
method A principled exploration of pruning, focusing on linear models and neural networks.
result Asymptotic formulas reveal the performance of different pruning methods.
Dirichlet pruning compresses neural networks by removing unimportant units.
problem Compressing large neural network models without sacrificing performance.
method Assigns Dirichlet distribution over network layers' units and uses variational inference to estimate parameters.
result Achieves state-of-the-art compression performance on larger architectures like VGG and ResNet.
Optimizes neural networks for solving problems with pruning and ensembles of minimal structures.
problem Improving neural network performance and interpretability.
method Pruning neural networks based on the principle of controlling training and pruning, using sensitivity indicators and logically transparent NN.
result Ensemble of minimal neural networks provides diverse forecasting algorithms and identifies areas for further data collection.
Neural network for subgraph similarity computation with pruning.
problem Computing subgraph similarity between a target and query graph.
method Convert pruning to node relabeling, relax to differentiable problem, design neural network for SED computation.
result Establishes new state-of-the-art results across multiple benchmark datasets.
SparseRT accelerates sparse computations on GPUs for deep learning inference.
problem Efficiently handling unstructured sparsity patterns on GPUs for deep learning.
method SparseRT, a code generator that leverages unstructured sparsity for accelerating sparse linear algebra operations.
result Geometric mean speedups of 3.4x at 90% sparsity and 5.4x at 95% sparsity for 1x1 convolutions and fully connected layers.
Real time application of deep learning algorithms is often hindered by high computational complexity and frequent memory accesses. Network pruning is a promising technique to solve this problem. However, pruning usually results in irregular network connections that not only demand extra representation efforts but also …
As a result of the growing size of Deep Neural Networks (DNNs), the gap to hardware capabilities in terms of memory and compute increases. To effectively compress DNNs, quantization and connection pruning are usually considered. However, unconstrained pruning usually leads to unstructured parallelism, which maps poorly…
New method grows deep networks efficiently by dynamically pruning and growing layers.
problem Training deep networks is computationally expensive and inefficient.
method Structured continuous sparsification starting from a small seed architecture.
result 49.7% inference FLOPs and 47.4% training FLOPs savings with 75.2% top-1 accuracy.
Holistic Filter Pruning reduces DNN complexity efficiently.
problem Redundant parameters in deep neural networks.
method Holistic Filter Pruning (HFP) for efficient DNN training.
result Achieves state-of-the-art performance with 60% reduction in multiplications on ImageNet.
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 w…
We introduce Delay Pruning, a simple yet powerful technique to regularize dynamic Boltzmann machines (DyBM). The recently introduced DyBM provides a particularly structured Boltzmann machine, as a generative model of a multi-dimensional time-series. This Boltzmann machine can have infinitely many layers of units but al…
Two retraining techniques outperform fine-tuning in neural network pruning.
problem Improving accuracy and compression in neural network pruning.
method Weight rewinding and learning rate rewinding compared to fine-tuning.
result Rewinding techniques outperform fine-tuning in accuracy and compression.
Neural network pruning is an important step in design process of efficient neural networks for edge devices with limited computational power. Pruning is a form of knowledge transfer from the weights of the original network to a smaller target subnetwork. We propose a new method for compute-constrained structured channe…
This paper finds a new way to compress CNN weights, improving on pruning and quantization.
problem Improving performance and storage efficiency of CNNs.
method Identifying and exploiting repeated patterns in CNN weight tensors, using Huffman coding and block sparse matrix formats.
result Achieved compaction ratios of 1.4x to 3.1x in addition to pruning and quantization.