No article text was recorded for this version.
least-squares weight reconstruction
Version 1 of 133 papers49 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Neuron Merging: Compensating for Pruned Neurons
- Blog: Fluctuation-Based Adaptive Structured Pruning for Large Language Models
- Blog: Linearly Replaceable Filters for Deep Network Channel Pruning
- Blog: Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models
- Blog: EAPruning: Evolutionary Pruning for Vision Transformers and CNNs
- Blog: Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning
- Blog: Diversity Networks Zelda Mariet
- Blog: A Fast Post-Training Pruning Framework for Transformers
- Blog: Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
- Blog: Numerical Pruning for Efficient Autoregressive Models
- Blog: Variance-Based Pruning for Accelerating and Compressing Trained Networks
- Blog: Exploiting Non-Linear Redundancy for Neural Model Compression
- Blog: Subspace Node Pruning
- Blog: Provable Repair of Deep Neural Networks
- Blog: FASP: Fast and Accurate Structured Pruning of Large Language Models
- Blog: Spectral Pruning for Recurrent Neural Networks
- Blog: Gradient-Free Structured Pruning with Unlabeled Data
- Blog: ModHiFi: Identifying High Fidelity predictive components for Model Modification
- Blog: Designing Energy-Efficient Convolutional Neural Networks Using Energy-Aware Pruning
- Blog: Revisiting Random Channel Pruning for Neural Network Compression
- Blog: OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization
- Blog: Syntactic vs Semantic Linear Abstraction and Refinement of Neural Networks
- Blog: Data-free parameter pruning for Deep Neural Networks
- Blog: Unfolding and Shrinking Neural Machine Translation Ensembles
- Blog: Data-Efficient Structured Pruning via Submodular Optimization
- Blog: OPTIMA: Optimal One-shot Pruning for LLMs via Quadratic Programming Reconstruction
- Blog: Sparsification via Compressed Sensing for Automatic Speech Recognition
- Blog: Diversity Networks
- Blog: Filter pruning-based two-step feature map reconstruction
- Blog: Channel Pruning for Accelerating Very Deep Neural Networks
- Blog: Model Preserving Compression for Neural Networks
- Blog: Unified Knowledge Maintenance Pruning and Progressive Recovery with Weight Recalling for Large Vision-Language Models
- Blog: GRAIL: Post-hoc Compensation by Linear Reconstruction for Compressed Networks
History & citation
Current · Permanent link
- This direction split from Structured Pruning via Layerwise Signal Reconstruction (58% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_least_squares_weight_reconstruction_9dbbe811,
title = {least-squares weight reconstruction},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/least-squares-weight-reconstruction/rdr_9dbbe811943d4fc4bb1beac6b070341c},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_least_squares_weight_reconstruction_9dbbe811_v1,
title = {least-squares weight reconstruction},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/least-squares-weight-reconstruction/rdr_9dbbe811943d4fc4bb1beac6b070341c/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}