No article text was recorded for this version.
hybrid low-rank and sparse decomposition
Version 1 of 126 papers34 conceptsfrozen 2026-10-04
Papers in this version
- Blog: LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression
- Blog: SLTrain: a sparse plus low rank approach for parameter and memory efficient pretraining
- Blog: Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization
- Blog: CMD: controllable matrix decomposition with global optimization for deep neural network compression
- Blog: On Compressing Deep Models by Low Rank and Sparse Decomposition
- Blog: LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation
- Blog: Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models
- Blog: Compressing by Learning in a Low-Rank and Sparse Decomposition Form
- Blog: MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning
- Blog: Model Compression with Adversarial Robustness: A Unified Optimization Framework
- Blog: Accelerating Transformer Inference and Training with 2:4 Activation Sparsity
- Blog: COSPADI: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning
- Blog: R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference
- Blog: Large Language Model Compression with Global Rank and Sparsity Optimization
- Blog: Scatterbrain: Unifying Sparse and Low-rank Attention
- Blog: 3BASiL: An Algorithmic Framework for Sparse plus Low-Rank Compression of LLMs
- Blog: A unified framework for Sparse plus Low-Rank Matrix Decomposition for LLMs
- Blog: Functional Connectivity Network Analysis with Discriminative Hub Detection for Brain Disease Identification
- Blog: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency
- Blog: OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition
- Blog: A3: an Analytical Low-Rank Approximation Framework for Attention
- Blog: Learning Parameter Sharing with Tensor Decompositions and Sparsity
- Blog: Alignment-Enhanced Integration of Connectivity and Spectral Sparsity in Dynamic Sparse Training of LLM
- Blog: Scaling Private Deep Learning with Low-rank and Sparse Gradients
- Blog: Targeted Low-rank Refinement: Enhancing Sparse Language Models with Precision
- Blog: Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace Offset
History & citation
Current · Permanent link
- This direction split from Sparse plus Low Rank Decomposition for Efficient Models (88% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_hybrid_low_rank_and_sparse_decomposition_dab549bb,
title = {hybrid low-rank and sparse decomposition},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/hybrid-low-rank-and-sparse-decomposition/rdr_dab549bb078c44ef87c7fa2ae8487af9},
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_hybrid_low_rank_and_sparse_decomposition_dab549bb_v1,
title = {hybrid low-rank and sparse decomposition},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/hybrid-low-rank-and-sparse-decomposition/rdr_dab549bb078c44ef87c7fa2ae8487af9/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}