Pith. sign in

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 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

background 1

representative citing papers

Transformers Don't In-Context Learn Least Squares Regression

cs.LG · 2025-07-13 · conditional · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Transformers Don't In-Context Learn Least Squares Regression cs.LG · 2025-07-13 · conditional · none · ref 4

    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.