Attention mechanisms trained on Gaussian data recover principal eigenvectors of the covariance matrix in finite and infinite prompt regimes.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Attention-based PCA
Attention mechanisms trained on Gaussian data recover principal eigenvectors of the covariance matrix in finite and infinite prompt regimes.