A new framework explains why early pruning works well.
problem Understanding why early pruning of neural networks leads to good performance.
method Gradient flow framework to unify pruning measures.
result Magnitude-based pruning removes least contributing parameters, leading to faster convergence.
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.
DSA efficiently allocates sparsity across layers for budgeted pruning.
problem Efficiently distributing resources (sparsity) across layers in pruning under resource constraints.
method DSA uses differentiable pruning to find continuous layer-wise pruning ratios via gradient-based optimization.
result DSA achieves superior performance and significantly reduces the time cost of pruning.
Gradient-based training and pruning for radial basis function networks in materials physics.
problem Interpretable and robust machine learning for materials physics problems.
method Gradient-based training and pruning of radial basis function networks with closed-form optimization criteria.
result Pruned models provide compact and interpretable versions of larger models, offering insights into atom-level migration processes.
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.
Improved pruning method finds winning neural network subnetworks.
problem Finding a small subnetwork that performs as well as a full neural network.
method Data-dependent pruning criterion using gradient of training loss.
result Data-dependent pruning improves existing pruning algorithms.
A new energy-efficient pruning method for federated learning.
problem Energy inefficiency in gradient sparsification for federated learning.
method Formalized energy-constrained projection problem and proposed Cost-Weighted Magnitude Pruning (CWMP).
result CWMP optimally balances performance and energy efficiency in federated learning.
Gradient-based method prunes large models to create transferable architectures.
problem Creating transferable architectures from large models with limited fine-tuning data.
method Gradient-based algorithm for architecture pruning and subset selection.
result Successfully retrain architectures on new tasks with few fine-tuning data.
Optimal defenses protect FL models from gradient reconstruction attacks.
problem Gradient reconstruction attacks compromise FL models by recovering original data from shared gradients.
method Derive a theoretical lower bound of reconstruction error, customize noise and pruning defenses, and achieve optimal trade-off between leakage and utility.
result Our methods outperform Gradient Noise and Pruning in protecting training data and maintaining model utility.
Pruning + fine-tuning reduces model complexity and generalizes well for matrix sensing.
problem Reducing model complexity for matrix sensing problems.
method Group Lasso regularization and greedy pruning.
result Pruning results in a solution with minimum columns close to the ground truth.
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.
A new pruning method finds sparse minimizers in flat regions of deep neural networks.
problem Finding sparse minimizers in flat regions of deep neural networks.
method Directional pruning using an ℓ1 proximal gradient algorithm. result Empirical results show promising sparsity (92%) and comparable minima to SGD.
New flaw found in SAP defense, reducing its effectiveness to 0.1%.
problem Weakness in Stochastic Activation Pruning defense against adversarial attacks.
method Re-examined the implementation of SAP and introduced a new BPDA attack.
result SAP's effectiveness reduced to 0.1% when properly applied.
Pruning neural networks improves feature learning in high-dimensional models.
problem Improving feature quality in high-dimensional statistical models.
method Demonstrated that pruning neural networks can optimally learn sparse models using gradient descent.
result Pruning neural networks proportional to the sparsity level of the model directions improves sample complexity.
Sparsification is an efficient approach to accelerate CNN inference, but it is challenging to take advantage of sparsity in training procedure because the involved gradients are dynamically changed. Actually, an important observation shows that most of the activation gradients in back-propagation are very close to zero…
Greedy selection finds smaller, more accurate subnetworks.
problem Finding smaller, accurate subnetworks in large neural networks.
method Greedy forward selection starting from an empty network.
result Theoretical guarantee of finding subnetworks with lower loss.
Bayesian Bits unifies quantization and pruning through gradient optimization.
problem Joint mixed precision quantization and pruning for efficient neural networks.
method Gradient-based optimization with a novel bit width decomposition and learnable stochastic gates.
result Bayesian Bits achieves better accuracy vs. efficiency trade-off compared to static bit width networks.
Hyperflux models pruning as a system to reveal weight importance.
problem Pruning large neural networks to reduce latency and power consumption.
method Introduces Hyperflux, a novel L0 method that models pruning as flux and pressure. result Achieves competitive results with ResNet-50, VGG-19, and DeiT-T/S on various datasets.
LTP learns per-layer thresholds for efficient pruning of deep networks.
problem Efficiently pruning deep neural networks to reduce computational cost and size.
method LTP learns thresholds via gradient descent, making pruning computationally efficient and scalable.
result LTP achieves competitive compression rates and maintains high accuracy on ImageNet networks.
Overparameterization has been shown to benefit both the optimization and generalization of neural networks, but large networks are resource hungry at both training and test time. Network pruning can reduce test-time resource requirements, but is typically applied to trained networks and therefore cannot avoid the expen…
Network pruning is a promising avenue for compressing deep neural networks. A typical approach to pruning starts by training a model and then removing redundant parameters while minimizing the impact on what is learned. Alternatively, a recent approach shows that pruning can be done at initialization prior to training,…
Improved TSK fuzzy regression models with MBGD-RDA and rule pruning.
problem Training and optimizing TSK fuzzy systems for regression tasks.
method MBGD-RDA algorithm with rule pruning for TSK fuzzy systems.
result Proposed MBGD-RDA variants and rule pruning improve performance and flexibility.
Overparameterized Neural Networks (NN) display state-of-the-art performance. However, there is a growing need for smaller, energy-efficient, neural networks tobe able to use machine learning applications on devices with limited computational resources. A popular approach consists of using pruning techniques. While thes…
New test improves tree ensemble pruning for better model performance.
problem Lack of robust theoretical justification for penalty terms in tree ensembles.
method Developed a novel hypothesis test for tree ensemble split quality.
result Significant reduction in out-of-sample loss using the new test.
Neural networks are easier to optimise when they have many more weights than are required for modelling the mapping from inputs to outputs. This suggests a two-stage learning procedure that first learns a large net and then prunes away connections or hidden units. But standard training does not necessarily encourage ne…
We propose a new formulation for pruning convolutional kernels in neural networks to enable efficient inference. We interleave greedy criteria-based pruning with fine-tuning by backpropagation - a computationally efficient procedure that maintains good generalization in the pruned network. We propose a new criterion ba…
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.
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.
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.
A new method prunes neural networks efficiently without losing effectiveness.
problem Efficient pruning of neural networks without sacrificing performance.
method Deterministic approximation of binary gates and L0 regularization. result Pruning neural networks significantly without loss in effectiveness.
Although deep neural networks (NNs) have achievedstate-of-the-art accuracy in many visual recognition tasks,the growing computational complexity and energy con-sumption of networks remains an issue, especially for ap-plications on platforms with limited resources and requir-ing real-time processing. Filter pruning tech…
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).
The study finds a theoretical bound for pre-training iterations needed for pruning to yield good subnetwork performance.
problem Discovering efficient subnetworks within pre-trained dense networks.
method Mathematical analysis of a two-layer, fully-connected network, validating with a multi-layer perceptron trained on MNIST.
result A logarithmically dependent threshold on dataset size for successful pruning.
New algorithm finds important synapses without training data.
problem Finding important synapses in neural networks without data.
method Iterative Synaptic Flow Pruning (SynFlow) based on conservation law.
result Algorithm consistently outperforms existing pruning methods.
Gradient descent on normalized networks reveals sparsity preferences.
problem Understanding the inductive bias of gradient descent on normalized neural nets.
method Analysis of gradient descent on weight-normalized smooth homogeneous neural nets, focusing on SWN and EWN.
result EWN causes weights to be updated in a way that prefers asymptotic relative sparsity.
Dynamic Vocabulary Pruning stabilizes LLM training by removing low-probability tokens.
problem Training Large Language Models (LLMs) with Reinforcement Learning (RL) causes numerical divergence between inference and training.
method Dynamic Vocabulary Pruning (DVP) constrains the RL objective to a safe vocabulary that excludes low-probability tokens.
result DVP stabilizes training by reducing systematic bias introduced by the extreme tail of the token distribution.
Deep Neural Network (DNN) is powerful but computationally expensive and memory intensive, thus impeding its practical usage on resource-constrained front-end devices. DNN pruning is an approach for deep model compression, which aims at eliminating some parameters with tolerable performance degradation. In this paper, w…
Pruning is a well-established technique for removing unnecessary structure from neural networks after training to improve the performance of inference. Several recent results have explored the possibility of pruning at initialization time to provide similar benefits during training. In particular, the "lottery ticket h…
We show implicit filter level sparsity manifests in convolutional neural networks (CNNs) which employ Batch Normalization and ReLU activation, and are trained with adaptive gradient descent techniques and L2 regularization or weight decay. Through an extensive empirical study (Mehta et al., 2019) we hypothesize the mec…
Powerpropagation makes neural networks inherently sparse.
problem Training sparse neural networks to reduce computational footprint and model size.
method Introduces a new weight-parameterisation technique exploiting gradient descent dynamics.
result Models trained with Powerpropagation have a higher density of zero weights, allowing for more efficient pruning.
It is inevitable to train large deep learning models on a large-scale cluster equipped with accelerators system. Deep gradient compression would highly increase the bandwidth utilization and speed up the training process but hard to implement on ring structure. In this paper, we find that redundant gradient and gradien…
The success of convolutional neural networks (CNNs) in various applications is accompanied by a significant increase in computation and parameter storage costs. Recent efforts to reduce these overheads involve pruning and compressing the weights of various layers while at the same time aiming to not sacrifice performan…
Survey on reducing deep neural network training complexity.
problem Efficient training of large deep neural networks.
method Pruning and freezing parts of the network during training.
result Dimensionality reduction improves training efficiency.
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.
FS&P uses birth-death process to ensure global convergence of stochastic conic particle gradient descent.
problem Global optimization of non-convex objective functions over measure space.
method Introduces Fast Spawn\&Prune (FS\&P) combining CPGD with birth-death process.
result First theoretical guarantee of global convergence for discrete-time stochastic algorithms.
Architecture optimization, which is a technique for finding an efficient neural network that meets certain requirements, generally reduces to a set of multiple-choice selection problems among alternative sub-structures or parameters. The discrete nature of the selection problem, however, makes this optimization difficu…
AdaDPIGU improves privacy in deep learning by adaptively clipping and pruning gradients.
problem Privacy in deep learning models, especially in high-dimensional settings.
method Importance-based gradient updates, adaptive clipping, differentially private SGD.
result AdaDPIGU achieves high accuracy while maintaining privacy, outperforming non-private models.
Stochastic Gradient TreeBoost is often found in many winning solutions in public data science challenges. Unfortunately, the best performance requires extensive parameter tuning and can be prone to overfitting. We propose PaloBoost, a Stochastic Gradient TreeBoost model that uses novel regularization techniques to guar…