This research investigates selectively pruning hyper and hypo neurons to improve neural network generalization.
problem Improving neural network generalization to unseen data.
method Investigates pruning hyper and hypo neurons selectively in fully connected layers of CNNs.
result Selective pruning of hyper and hypo neurons improves model performance on out-of-domain data.
Paper proposes a faster DNN pruning method.
problem Efficiently prune DNNs without sacrificing accuracy.
method Uses PCA to automatically optimize pruning.
result Prunes DNNs in one shot, no retraining needed.
SeReNe prunes neurons with low sensitivity to reduce network size.
problem Large neural networks consume too many resources on resource-constrained devices.
method Exploits neural sensitivity as a regularizer to prune neurons with low sensitivity.
result Pruning neurons with low sensitivity achieves competitive compression ratios.
TENP prunes experts and neurons in Mixture-of-Experts models for efficient deployment.
problem Efficient deployment of large language models constrained by static parameter footprint.
method Structured Trapezoidal ExpertNeuron Pruning (TENP) identifies and retains important experts and neurons.
result DeepSeek model achieves 10% better performance on code generation tasks with 40% expert sparsity.
Structured pruning method reduces RNN sizes and speeds up inference.
problem Large RNN models are hard to deploy on edge devices.
method Structured pruning through neuron selection, minimizing L0 norm of weight matrix.
result Nearly 20x speedup achieved without performance loss.
CLNP improves lifelong learning in fixed capacity models by pruning and reusing neurons.
problem Improving lifelong learning in fixed capacity models.
method Neural pruning and reuse of inactive neurons with graceful forgetting concept.
result CLNP leads to significantly improved results over current methods.
BSF algorithm reduces neural network size and selects features efficiently.
problem Neural network size and feature selection optimization.
method Binary Stochastic Filtering (BSF) layer that penalizes information, stochastically passes or drops features.
result Multifold decrease in neural network size and optimal feature selection.
OPNP prunes parameters and neurons to improve OOD detection without training.
problem Detecting out-of-distribution samples in real-world machine learning models.
method OPNP approach that identifies and removes sensitive parameters and neurons.
result OPNP consistently outperforms existing methods on multiple OOD detection tasks.
Mixed integer programming identifies critical neurons in neural networks.
problem Identifying neurons critical for network performance and generalization.
method Developed a mixed integer program (MIP) to assign importance scores to neurons, guiding pruning decisions.
result The method identifies multiple 'lucky' sub-networks resulting in optimized architectures that generalize across datasets.
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…
Partial fusion combines neural networks to balance accuracy and efficiency.
problem Balancing accuracy and computational cost in neural networks.
method Extending weight aggregation methods based on neuron-level similarity, using partial optimal transport to match similar neurons.
result Achieves a flexible tradeoff between computational cost and performance.
This work improves neural network compression by jointly pruning weights and activations.
problem Improving deployment efficiency of deep neural networks.
method Joint regularization technique that simultaneously prunes weights and activations.
result Jointly pruned network (JPnet) achieves significant computation cost reduction.
Survey on pruning CNN models to reduce size for edge devices.
problem Reducing large CNN models for edge deployment.
method Comprehensive review of pruning strategies, criteria, and techniques.
result Pruning accelerates CNN models for edge applications.
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.
New Lipschitz bound for ReLU networks resists weight rescaling.
problem Lack of robustness guarantees for ReLU networks under weight perturbations.
method Rescaling-invariant Lipschitz bound based on path-metrics.
result The new bound applies to various ReLU-DAG architectures and resists neuron-wise rescalings.
Network pruning is aimed at imposing sparsity in a neural network architecture by increasing the portion of zero-valued weights for reducing its size regarding energy-efficiency consideration and increasing evaluation speed. In most of the conducted research efforts, the sparsity is enforced for network pruning without…
Data-independent pruning method reduces neural network size with accuracy guarantees.
problem Limited computational and memory resources for neural networks.
method Structured pruning using coresets.
result First efficient algorithm with worst-case guarantees on compression and accuracy.
Theoretical framework for neural network compression using sparsity norms.
problem Understanding and quantifying compressibility and accuracy trade-offs in neural networks.
method Using sparsity-sensitive ℓ_q-norm to characterize compressibility and developing adaptive pruning algorithms.
result Theoretical relationship between network sparsity and compressibility with controlled accuracy degradation.
New method prunes recurrent networks efficiently, improving performance.
problem Pruning recurrent neural networks (RNNs) is challenging and often leads to poor performance.
method Data-efficient pruning objective derived from the spectrum of the recurrent Jacobian.
result 95% sparse GRUs significantly improve on existing baselines.
Simple iterative method reduces deep network size significantly.
problem Overparameterization of deep neural networks in compute-limited systems.
method Hybrid approach combining single shot pruning and Lottery-Ticket methods.
result State-of-the-art compression achieved with improved test accuracy and compression ratio.
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.
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.
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.
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.
Pruned neural networks learn digital circuits with 99% weight reduction.
problem Efficiently train deep neural networks with minimal weights.
method Constrained binarized networks to zero or one weights.
result Pruned networks achieve similar performance to standard networks with 99% weight reduction.
As neural networks become widely deployed in different applications and on different hardware, it has become increasingly important to optimize inference time and model size along with model accuracy. Most current techniques optimize model size, model accuracy and inference time in different stages, resulting in subopt…
Data-independent neural pruning via coresets improves accuracy with 90% compression.
problem Efficiently reduce neural network size while maintaining accuracy.
method Data-independent neural pruning using coresets.
result 90% compression of LeNet-300-100 on MNIST with improved accuracy.
This paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The model provides adaptive and differentiable local connectivity (plasticity) applicable to any domain. It requires no other tool than the backpropagation algorithm to learn its parameters whi…
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.
A method estimates and prunes neural network filters to reduce computation and improve accuracy.
problem Reduction of neural network parameters to save computation and energy.
method Estimates each neuron's contribution to loss using first and second-order Taylor expansions; iteratively removes less important neurons.
result High (>93%) correlation between estimated and true importance; 40% FLOPS reduction with 0.02% top-1 accuracy loss.
Logarithmic pruning simplifies lottery ticket hypothesis.
problem Finding efficient subnetworks in large neural networks.
method Logarithmic pruning approach to identify subnetworks.
result Randomly initialized subnetworks achieve comparable performance.
New learning algorithm mimics biological neural networks.
problem Biologically implausible backpropagation for directed neural networks.
method Introduces new neuronal dynamics and learning rule for arbitrary architectures, sparsity-inducing pruning method, and dynamical-systems characterization.
result Prunes irrelevant connections and improves learning efficiency.
TX-Ray analyzes and quantifies model knowledge transfer in NLP.
problem Insufficient methods for explaining and quantifying model knowledge transfer in NLP.
method Modified computer vision explainability principle to NLP, visualizing feature preference distributions.
result TX-Ray reveals how self-supervised models learn linguistic abstractions and improves generalization.
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.
New SDP method certifies neural network robustness across all classes efficiently.
problem Certifying robustness of neural networks across multiple classes.
method Quadratic model + SDP relaxation + pruning strategy.
result Significant computational speed-up and scalability to large datasets.
Paper proposes neural network for efficient MIMO channel estimation and pilot reduction.
problem High overhead from pilot transmission in wideband MIMO systems.
method Neural network architecture for frequency-aware pilot design and channel estimation, with pruning technique.
result Neural network outperforms linear minimum mean square error (LMMSE) estimation.
Improves parallel deep model performance by restructuring and pruning.
problem Latency in parallel deep model execution due to interdependency among sub-models.
method Layer-wise model restructuring and pruning, using ℓ0 optimization and Munkres assignment algorithm. result Significantly improves efficiency of distributed inference in terms of communication and computational complexity.
Sparser Random Feature Models via IMP (ShRIMP) efficiently learns sparse models for high-dimensional data.
problem Learning sparse models for high-dimensional data with sparse variable dependencies.
method Iterative Magnitude Pruning applied to Random Feature Models.
result ShRIMP achieves better or competitive test accuracy compared to state-of-the-art methods.
The study examines if ReLU activation function is optimal for modularity in neural networks.
problem Finding the best activation function for modularity in neural networks.
method Comparing ReLU with other activation functions for modularity and performance.
result ReLU may not be the best choice for modularity, suggesting other functions could be more suitable.
Model neural plasticity as binary optimization to dynamically activate or deactivate network units.
problem Dynamic learning and adaptability of neural networks.
method Model neural plasticity as an L0-norm regularized binary optimization problem, where units can be activated or deactivated based on a cost-benefit tradeoff. result Demonstrates that a single parameter k can modulate learning dynamics, unifying network sparsification and expansion. A new method sparsifies neural networks using stochastic binary optimization.
problem Sparsifying neural networks to reduce computational cost and improve efficiency.
method Stochastic binary optimization with the Augment-Reinforce-Merge (ARM) estimator.
result ARM enables efficient network sparsification with comparable accuracy to baseline methods.
A new method identifies a stable subnetwork in overparameterized student models.
problem Identifying a stable subnetwork in overparameterized student models.
method Spectral representation of linear transfer of information, focusing on eigenvalues and eigenvectors.
result A stable student substructure is isolated that mirrors the true complexity of the teacher.
Dropout-based regularization methods can be regarded as injecting random noise with pre-defined magnitude to different parts of the neural network during training. It was recently shown that Bayesian dropout procedure not only improves generalization but also leads to extremely sparse neural architectures by automatica…
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.