Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations.
Bowen ShenZheng LinDaren ZhaWei LiuJian LuanBin WangWeiping WangPublished in: CoRR (2024)
Keyphrases
- language model
- low rank
- language modeling
- missing data
- matrix factorization
- convex optimization
- linear combination
- singular value decomposition
- low rank matrix
- n gram
- rank minimization
- probabilistic model
- document retrieval
- query expansion
- matrix completion
- test collection
- information retrieval
- retrieval model
- high order
- semi supervised
- high dimensional data
- vector space model
- trace norm
- smoothing methods
- query terms
- dimensionality reduction
- collaborative filtering
- relevance model
- pattern recognition
- image processing
- data mining
- language models for information retrieval