A Gaussian graphical model with non-convex group sparsity selects a small set of singular components of a pretrained model to fine-tune, achieving competitive GLUE performance with 0.084M trainable parameters.
Qlora: efficient finetuning of quantized llms
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2024 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Adaptive Principal Components Allocation with the $\ell_{2,g}$-regularized Gaussian Graphical Model for Efficient Fine-Tuning Large Models
A Gaussian graphical model with non-convex group sparsity selects a small set of singular components of a pretrained model to fine-tune, achieving competitive GLUE performance with 0.084M trainable parameters.