No article text was recorded for this version.
layer collapse
Version 1 of 166 papers82 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Plant 'n' Seek: Can You Find the Winning Ticket?
- Blog: Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!
- Blog: Restricted Random Pruning at Initialization for High Compression Range
- Blog: Is Complexity Required for Neural Network Pruning? A Case Study on Global Magnitude Pruning
- Blog: The rise of the lottery heroes: why zero-shot pruning is hard
- Blog: Rare Gems: Finding Lottery Tickets at Initialization
- Blog: Robust Pruning at Initialization
- Blog: Pruning neural networks without any data by iteratively conserving synaptic flow
- Blog: Pruning Neural Networks at Initialization: Why Are We Missing the Mark?
- Blog: Picking Winning Tickets Before Training by Preserving Gradient Flow
- Blog: Sparse Training with Lipschitz Continuous Loss Functions and a Weighted Group L0-norm Constraint
- Blog: Win the Lottery Ticket via Fourier Analysis: Frequencies Guided Network Pruning
- Blog: CoNNect: Connectivity-Based Regularization for Structural Pruning of Neural Networks
- Blog: Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks
- Blog: Picking Winning Tickets Before Training by Preserving Gradient Flow
- Blog: RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs
- Blog: Trainability Preserving Neural Pruning
- Blog: Compressing Deep Networks by Neuron Agglomerative Clustering
- Blog: Considering Layerwise Importance in the Lottery Ticket Hypothesis
- Blog: LEAN: graph-based pruning for convolutional neural networks by extracting longest chains
- Blog: 2SSP: A Two-Stage Framework for Structured Pruning of LLMs
- Blog: Pruning untrained neural networks: Principles and Analysis
- Blog: Why Random Pruning Is All We Need to Start Sparse
- Blog: A Three-regime Model of Network Pruning
- Blog: Boomerang Distillation Enables Zero-Shot Model Size Interpolation
- Blog: EGGS-PTP: An Expander-Graph Guided Structured Post-training Pruning Method for Large Language Models
- Blog: PHEW : Constructing Sparse Networks that Learn Fast and Generalize Well without Training Data
- Blog: What Scalable Second-Order Information Knows for Pruning at Initialization
- Blog: Training Your Sparse Neural Network Better with Any Mask
- Blog: Fishing For Cheap And Efficient Pruners At Initialization
- Blog: Probabilistic Neural Pruning via Sparsity Evolutionary Fokker-Planck-Kolmogorov Equation
- Blog: PHEW : Constructing Sparse Networks that Learn Fast and Generalize Well without Training Data
- Blog: Deep Neural Network Pruning for Nuclei Instance Segmentation in Hematoxylin & Eosin-Stained Histological Images
- Blog: Arboreal Neural Network
- Blog: SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization
- Blog: Understanding and Accelerating Neural Architecture Search With Training-Free and Theory-Grounded Metrics
- Blog: A Study on the Ramanujan Graph Property of Winning Lottery Tickets
- Blog: A Fair Loss Function for Network Pruning
- Blog: PruningBench: A Comprehensive Benchmark of Structural Pruning
- Blog: Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning
- Blog: FedOBD: Opportunistic Block Dropout for Efficiently Training Large-scale Neural Networks through Federated Learning
- Blog: Avoiding Overfitting with BP-SOM
- Blog: Sparsest Models Elude Pruning: An Exposé of Pruning’s Current Capabilities
- Blog: Training Your Sparse Neural Network Better with Any Mask
- Blog: Multi-Layer Pruning Framework for Compressing Single Shot MultiBox Detector
- Blog: RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs
- Blog: PHEW: Paths with higher edge-weights give "winning tickets" without training data
- Blog: Pruning Neural Networks at Initialization: Why are We Missing the Mark?
- Blog: Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace Offset
- Blog: NTK-SAP: Improving neural network pruning by aligning training dynamics
- Blog: CoNNect: A Swiss-Army-Knife Regularizer for Pruning of Neural Networks
- Blog: Dynamic Hard Pruning of Neural Networks at the Edge of the Internet
- Blog: Plug-and-Play: An Efficient Post-training Pruning Method for Large Language Models
- Blog: Pushing the Efficiency Limit Using Structured Sparse Convolutions
- Blog: Pruning neural networks without any data by iteratively conserving synaptic flow
- Blog: Fast Convex Pruning of Deep Neural Networks
- Blog: MoNE: Replacing Redundant Experts with Lightweight Novices for Structured Pruning of MoE
- Blog: Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions
- Blog: HyperSparse Neural Networks: Shifting Exploration to Exploitation through Adaptive Regularization
- Blog: Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM)
Showing 60 of 66 papers.
History & citation
Current · Permanent link
- Preserving the Topological Skeleton of Sparse Neural Networks merged into this direction (61% overlap)
- This direction split from Preserving Signal Flow to Prevent Layer Collapse (74% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_layer_collapse_2378d39e,
title = {layer collapse},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/layer-collapse/rdr_2378d39ed3e8436ea2168ae7dd04021d},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_layer_collapse_2378d39e_v1,
title = {layer collapse},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/layer-collapse/rdr_2378d39ed3e8436ea2168ae7dd04021d/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}