LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation.
Yixiao LiYifan YuQingru ZhangChen LiangPengcheng HeWeizhu ChenTuo ZhaoPublished in: ICML (2023)
Keyphrases
- language model
- language modeling
- low rank and sparse
- document retrieval
- probabilistic model
- information retrieval
- n gram
- query expansion
- statistical language models
- test collection
- retrieval model
- image compression
- language modelling
- mixture model
- convex optimization
- signal recovery
- smoothing methods
- low rank
- machine learning
- semi supervised
- relevance model
- language models for information retrieval