No article text was recorded for this version.
irreversible pruning
Version 2 of 288 papers89 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Growing Winning Subnetworks, Not Pruning Them: A Paradigm for Density Discovery in Sparse Neural Networks
- Blog: ROSE: Reordered SparseGPT for More Accurate One-Shot Large Language Models Pruning
- Blog: Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks
- Blog: Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks
- Blog: Neural Plasticity Networks
- Blog: Cooperative Pruning in Cross-Domain Deep Neural Network Compression
- Blog: SUBP: Soft Uniform Block Pruning for 1$\times$N Sparse CNNs Multithreading Acceleration
- Blog: Early Brain Damage
- Blog: MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks
- Blog: DropPruning for Model Compression
- Blog: State Transition of Dendritic Spines Improves Learning of Sparse Spiking Neural Networks
- Blog: Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers
- Blog: SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning
- Blog: Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch
- Blog: FlexHiNM-GP: Flexible Hierarchical Pruning via Region Allocation and Channel Permutation
- Blog: Pruning of Deep Spiking Neural Networks through Gradient Rewiring
- Blog: Pruning by Block Benefit: Exploring the Properties of Vision Transformer Blocks during Domain Adaptation
- Blog: Accelerating Convolutional Networks via Global & Dynamic Filter Pruning
- Blog: Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolution
- Blog: PDP: Parameter-free Differentiable Pruning is All You Need
- Blog: COPAL: Continual Pruning in Large Language Generative Models
- Blog: SAS: Structured Activation Sparsification
- Blog: Gradient-based Gradual Pruning for Language-Specific Multilingual Neural Machine Translation
- Blog: Efficient DNN Neuron Pruning by Minimizing Layer-wise Nonlinear Reconstruction Error
- Blog: Dynamic Network Surgery for Efficient DNNs
- Blog: SUBP: Soft Uniform Block Pruning for 1xN Sparse CNNs Multithreading Acceleration
- Blog: Efficient Network Construction Through Structural Plasticity
- Blog: MoEfication: Transformer Feed-forward Layers are Mixtures of Experts
- Blog: HyperSparse Neural Networks: Shifting Exploration to Exploitation through Adaptive Regularization
- Blog: DRNet: Dissect and Reconstruct the Convolutional Neural Network via Interpretable Manners
- Blog: Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes
- Blog: PROXSPARSE: REGULARIZED LEARNING OF SEMI-STRUCTURED SPARSITY MASKS FOR PRETRAINED LLMS
- Blog: Adaptive Sparsity Level During Training for Efficient Time Series Forecasting with Transformers
- Blog: Towards efficient deep spiking neural networks construction with spiking activity based pruning
- Blog: GHFP: Gradually Hard Filter Pruning
- Blog: Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning
- Blog: Design of a Very Compact CNN Classifier for Online Handwritten Chinese Character Recognition Using DropWeight and Global Pooling
- Blog: BWCP: Probabilistic Learning-to-Prune Channels for ConvNets via Batch Whitening
- Blog: Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization
- Blog: Structured Deep Neural Network Pruning by Varying Regularization Parameters
- Blog: Auto- Train-Once: Controller Network Guided Automatic Network Pruning from Scratch
- Blog: Towards Efficient Deep Spiking Neural Networks Construction with Spiking Activity based Pruning
- Blog: Frequency-Domain Dynamic Pruning for Convolutional Neural Networks
- Blog: Modified Dirichlet Distribution: Allowing Negative Parameters to Induce Stronger Sparsity
- Blog: Pruning of Deep Spiking Neural Networks through Gradient Rewiring
- Blog: Compressing Deep Reinforcement Learning Networks with a Dynamic Structured Pruning Method for Autonomous Driving
- Blog: Sparse Invariant Risk Minimization
- Blog: Soft Masking for Cost-Constrained Channel Pruning
- Blog: "Learning-Compression" Algorithms for Neural Net Pruning
- Blog: Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization
- Blog: Cyclical Pruning for Sparse Neural Networks
- Blog: FlexLoRA: Entropy-Guided Flexible Low-Rank Adaptation
- Blog: Extended Regularization Methods for Nonconvergent Model Selection
- Blog: Feature Selection using Stochastic Gates
- Blog: ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection
- Blog: Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio
- Blog: Iteratively Training Look-Up Tables for Network Quantization
- Blog: PDP: Parameter-free Differentiable Pruning is All You Need
- Blog: Softer Pruning, Incremental Regularization
- Blog: Cascaded channel pruning using hierarchical self-distillation
Showing 60 of 88 papers.
History & citation
Current · Permanent link
- dynamic weight revival split from this direction (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_irreversible_pruning_7900b111,
title = {irreversible pruning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/irreversible-pruning/rdr_7900b11133da46039fd7bbc202daf68e},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_irreversible_pruning_7900b111_v2,
title = {irreversible pruning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/irreversible-pruning/rdr_7900b11133da46039fd7bbc202daf68e/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}