In-context regression transformers do not approximate OLS: they underperform it even in-distribution, fail on out-of-subspace prompts, and their failures correlate with a low-rank spectral signature in the residual stream.
Training with noise is equivalent to tikhonov regularization
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Transformers Don't In-Context Learn Least Squares Regression
In-context regression transformers do not approximate OLS: they underperform it even in-distribution, fail on out-of-subspace prompts, and their failures correlate with a low-rank spectral signature in the residual stream.