Unified framework for accelerating DNNs on resource-limited platforms.
problem Accelerating DNN execution on resource-limited platforms.
method Block-based pruning framework with reweighted regularization.
result First universal framework for both CNNs and RNNs with real-time acceleration and no accuracy compromise.
This paper introduces GLT for better input data representation in BNN and proposes a compact topology with block pruning.
problem Improving input data representation for Binary Neural Networks (BNN).
method Generic Learned Thermometer (GLT) for encoding, block pruning and Knowledge Distillation for compact topology.
result Significant accuracy gains and lightweight fully-binarized models with limited accuracy degradation.
Recurrent Neural Networks (RNNs) are used in state-of-the-art models in domains such as speech recognition, machine translation, and language modelling. Sparsity is a technique to reduce compute and memory requirements of deep learning models. Sparse RNNs are easier to deploy on devices and high-end server processors. …
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…
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.
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.
The enormous size of modern deep neural networks makes it challenging to deploy those models in memory and communication limited scenarios. Thus, compressing a trained model without a significant loss in performance has become an increasingly important task. Tremendous advances has been made recently, where the main te…
Recurrent Neural Networks (RNNs) are becoming increasingly important for time series-related applications which require efficient and real-time implementations. The recent pruning based work ESE suffers from degradation of performance/energy efficiency due to the irregular network structure after pruning. We propose bl…
Paper proposes a framework and algorithm for model compression in neural networks.
problem Training neural networks with model compression techniques suffers from accuracy loss and convergence issues.
method Holistic framework based on nonconvex optimization, using NN-BCD algorithm with closed-form iteration scheme.
result The proposed algorithm globally converges to a critical point at a rate of O(1/k).
New algorithm PRACTISE accelerates networks with tiny sets, reducing latency by 22%.
problem Accelerating networks with tiny training sets to improve performance and privacy.
method Proposes a new algorithm PRACTISE based on finetune convexity hypothesis and feature mimicking.
result PRACTISE outperforms previous methods by reducing latency by 22% on ImageNet-1k.
Deep neural network compression techniques such as pruning and weight tensor decomposition usually require fine-tuning to recover the prediction accuracy when the compression ratio is high. However, conventional fine-tuning suffers from the requirement of a large training set and the time-consuming training procedure. …
Proves a conjecture about 3-manifold invariants using trees and asymptotic formulas.
problem Proving the holomorphy of certain rational functions for plumbed 3-manifolds.
method Induction on a sequence of trees, using the Euler-Maclaurin summation formula.
result Proves the conjecture about Witten-Reshetikhin-Turaev invariants and homological blocks.
Study shows LLMs can remove half of layers without significant performance drop.
problem Understanding knowledge storage in LLMs' weights.
method Layer pruning and finetuning to identify and remove unnecessary parameters.
result Minimal degradation of performance after removing up to half of layers.
SubSearch detects graph outliers and estimates SBM parameters robustly.
problem Real-world graphs often deviate from ideal SBM assumptions.
method Subgraph search to find subgraphs that align with SBM assumptions.
result SubSearch accurately estimates SBM parameters and detects outliers.
Large-scale deep neural networks (DNNs) are both compute and memory intensive. As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performance while maintaining accuracy. For DNNs, the model size is an important factor affecting performance, scalability and energy efficiency. Weig…
Lookahead pruning extends single-layer optimization to multi-layer, outperforming magnitude-based pruning.
problem Pruning neural networks to reduce computational cost and memory usage.
method Developed a multi-layer optimization approach extending the single-layer optimization of magnitude-based pruning.
result Consistently outperforms magnitude-based pruning on various networks, especially in high sparsity.
Recent pruning methods at initialization fall short of random pruning's accuracy.
problem Improving neural network accuracy through pruning at initialization.
method Various pruning methods (SNIP, GraSP, SynFlow, magnitude pruning) are evaluated; per-layer pruning decisions are proposed.
result Randomly shuffling or sampling initial weights preserves or improves accuracy, suggesting challenges with pruning heuristics.
ICE-Pruning accelerates deep neural network pruning by 9.61x.
problem Efficiently pruning deep neural networks while maintaining accuracy.
method Iterative pruning with automatic fine-tuning steps, freezing strategy, and custom learning rate scheduler.
result Significantly reduces pruning time by up to 9.61x.
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.
Study examines effects of pruning techniques on deep learning models.
problem Understanding the impact of pruning methods on deep learning model structure and dynamics.
method Investigated differences in connectivity and learning dynamics of pruned models using various iterative pruning techniques.
result Emergence of structure in pruned models through magnitude-based unstructured pruning and weight rewinding.
Paper presents privacy-preserving techniques for HD computing.
problem Privacy loss in HD computing due to reversible computation.
method Quantization and pruning of hypervectors for differential privacy.
result Differentially private HD model for cloud inference.
Pruning neural network parameters is often viewed as a means to compress models, but pruning has also been motivated by the desire to prevent overfitting. This motivation is particularly relevant given the perhaps surprising observation that a wide variety of pruning approaches increase test accuracy despite sometimes …
Dynamic pruning during training reduces deep network complexity without significant accuracy loss.
problem High memory and computational requirements of deep networks during training and inference.
method Dynamic pruning of convolutional filters during training, using L1 normalization for optimization.
result L1 normalization-based pruning yields up to 50% reduction in filters with minimal accuracy loss.
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.
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…
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.
New statistical mechanics analysis shows edge pruning outperforms node pruning in neural networks.
problem Theoretical understanding of neural network pruning effectiveness is lacking.
method Statistical mechanics analysis of a teacher-student framework.
result DPP node pruning method is superior to other methods, but edge pruning is better overall.
This paper introduces blind adversarial pruning to balance accuracy, efficiency, and robustness in neural networks.
problem Balancing accuracy, efficiency, and robustness in neural networks with limited resources.
method Adversarial pruning with a cutoff-scale strategy to dynamically adjust the strength of adversarial examples.
result Blind adversarial pruning improves the overall AER of pruned models compared to adversarial pruning.
HOPE uses Hilbert space to deconstruct deep network representations.
problem Deconstructing learned representations in deep networks is challenging.
method Introduces Hilbert Operator for Progressive Encoding (HOPE) to deconstruct network weights.
result HOPE provides an unbiased approach to network compression and fine-tuning.
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.
This paper analyzes privacy risks in neural network pruning and proposes a defense mechanism.
problem Privacy risks in neural network pruning due to membership inference attacks.
method Investigates the impact of pruning on prediction divergence and proposes a self-attention membership inference attack.
result Proposed defense mechanism mitigates privacy risks while maintaining sparsity and accuracy.
Neural network pruning lacks standardized benchmarks and metrics.
problem Lack of standardized benchmarks and metrics in neural network pruning.
method Meta-analysis of 81 papers, controlled conditions, ShrinkBench framework.
result Neural network pruning community lacks standardized benchmarks and metrics.
Bayesian inference improves neural network pruning efficiency.
problem Reducing computational and memory demands of large neural networks.
method Utilizes Bayesian inference to calculate Bayes factors for iterative pruning.
result Achieves desired levels of sparsity while maintaining competitive accuracy.
AlphaPruning optimizes LLM pruning using HT-SR theory for better performance.
problem Improving pruning of large language models to reduce size without sacrificing performance.
method AlphaPruning uses HT-SR theory to allocate layerwise sparsity ratios more theoretically.
result AlphaPruning prunes LLaMA-7B to 80% sparsity with reasonable perplexity.
This work characterizes the fundamental limit of network pruning using statistical dimension and convex geometry.
problem The fundamental limit of network pruning is still lacking, especially for deep neural networks.
method Directly imposing sparsity constraint on the loss function and using statistical dimension in convex geometry.
result Characterizes the sharp phase transition point as the fundamental limit of pruning ratio.
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.
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.
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.
A method to combine saliency metrics for better CNN pruning decisions.
problem Improving CNN pruning decisions by combining multiple saliency metrics.
method Proposes a method to compose different saliency metrics for better CNN pruning decisions.
result The composition of saliencies avoids many poor pruning choices identified by individual saliencies.
Pruning improves model generalization in over-parameterized models, contradicting traditional theories.
problem Pruning's effect on generalization in over-parameterized models.
method Empirical study on standard pruning algorithms and additional regularization effects.
result Pruning leads to better training and regularization, improving generalization.
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.
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.
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.
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,…
Data pruning algorithms struggle in high compression regimes, as shown by theoretical and empirical studies.
problem Limitations of score-based data pruning algorithms in high compression regimes.
method Theoretical and empirical analysis of score-based data pruning algorithms.
result Score-based data pruning algorithms fail in high compression regimes due to 'No Free Lunch' theorems.
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.
Deep neural networks (DNNs) although achieving human-level performance in many domains, have very large model size that hinders their broader applications on edge computing devices. Extensive research work have been conducted on DNN model compression or pruning. However, most of the previous work took heuristic approac…
PruneNet efficiently prunes channels in deep networks, improving accuracy and performance.
problem Improving deep neural network performance and efficiency through channel pruning.
method PruneNet uses a computationally light-weight optimization step to identify and prune channels based on layer redundancy.
result Pruned ResNet models achieve higher accuracy and better performance than non-pruned models.