Transformers converge globally to the optimal DDPM denoiser for multi-token GMMs via self-attention mean denoising, with explicit token and iteration requirements.
Transformers provably learn feature-position correlations in masked image modeling
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs
Transformers converge globally to the optimal DDPM denoiser for multi-token GMMs via self-attention mean denoising, with explicit token and iteration requirements.