Author

G. Planes

h-index 1 View on Semantic Scholar

We have 1 of 3 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

How Much Rank Does LoRA Need? Rank-Error Bounds for Transformer Attention

This paper provides a task-dependent theory of the approximation error achievable at each LoRA rank for Transformer attention, and extends the analysis to fused multi-head LoRA and joint query/key updates, exposing the effects of rank sharing and query/key factorization constraints.

G. Planes · 0 citations