In-context learning lets LLMs approximate p-norms, nuclear norms, and top singular values of matrices, outperforming SGD, 2-layer nets, and CNNs on the harder SVD tasks in the authors' small-scale tests.
Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Can a Large Language Model Learn Matrix Functions In Context?
In-context learning lets LLMs approximate p-norms, nuclear norms, and top singular values of matrices, outperforming SGD, 2-layer nets, and CNNs on the harder SVD tasks in the authors' small-scale tests.