No AI summary available for this article.
Why It Matters
Newton-Schulz (NS) iteration has recently been used in the Muon optimizer to transform update matrices during the training of large language models.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Newton-Schulz (NS) iteration has recently been used in the Muon optimizer to transform update matrices during the training of large language models. Motivated by its spectral effect, we investigate applying NS directly to Transformer attention representations. We introduce Newton-Schulz Attention (NS-Attn.), a parameter-free transformation applied to the output of each attention head. Each head output is arranged as a feature-by-token matrix and normalized by its Frobenius norm. We then apply a finite NS polynomial step and restore the original norm. The objective is to reduce spectral concent...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.27735v1 · Indexed about 2 hours ago