oai-math-revised beta

Browse › Theoretical computer science › 135 Homogeneous depth-five lower bounds for iterated matrix multiplication

Homogeneous depth-five lower bounds for iterated matrix multiplication

OpenAI · September 25, 2026

Lean

Open PDFCite Report a problem Add a reference or comment Interested in working on this Start a discussion

Edit NOTES.md · Existing issues · Source on GitHub

Abstract

Let $\mathop{\mathrm{IMM}}\nolimits _{n,n}$ be the $(1,1)$ entry of a product of n independent $n\times n$ matrices of variables. Over every field of characteristic zero, every syntactically homogeneous $\Sigma\Pi\Sigma\Pi\Sigma$ circuit computing $\mathop{\mathrm{IMM}}\nolimits _{n,n}$ has at least $n^{\sqrt n/400}$ gates for all sufficiently large n, with an absolute threshold independent of the field. Bottom linear forms may have arbitrary support, and arbitrary finite fan-in, fan-out, and gate sharing are allowed. Over every field, a block expansion gives such circuits with at most $n^{\sqrt n+4}$ gates for n ≥ 2. Thus the gate complexity over characteristic-zero fields is $n^{\Theta(\sqrt n)}$.

If the PDF does not display here, open it directly: Open PDF.

Notes

No notes yet. Add a reference, a comment or your name with the buttons above, or edit NOTES.md on GitHub.

Automatically collected notes (unreviewed)

work in progress

Collected automatically by AI tools (Claude Opus 5.5 and GPT-6 Astra, 2026-10-21) and not checked by a person. May be wrong or incomplete. Report an error.

Formalization

  • OpenAI, Homogeneous depth-five lower bounds for iterated matrix multiplication: Lean scope note (OpenAI math release, lean/docs/135.md, 2026-10-06). The scope note says the formalization covers the $n^{\sqrt n/400}$ lower bound over every characteristic-zero field (field-independent threshold, unrestricted bottom support and sharing) and the $n^{\sqrt n+4}$ upper bound over every field, and it points to the comparator statement lean/ComparatorChallenges/DepthFive.lean.

Possibly relevant literature (found by the agent, not checked)

Digests and expositions

Elsewhere

Independent sites; their content is not reviewed here.

Cite

@misc{OAI:Homogeneous-depth-five-lower-bounds-for-iterated-matrix-multiplication-September-25-2026,
  author = {{OpenAI}},
  title = {{Homogeneous depth-five lower bounds for iterated matrix multiplication}},
  howpublished = {OpenAI Math Release preprint
                  \href{https://github.com/openai/math/blob/main/preprints/Homogeneous-depth-five-lower-bounds-for-iterated-matrix-multiplication-September-25-2026/Homogeneous-depth-five-lower-bounds-for-iterated-matrix-multiplication-September-25-2026.pdf}{OAI:Homogeneous-depth-five-lower-bounds-for-iterated-matrix-multiplication-September-25-2026}},
  year = {2026}
}

Lean formalization

OpenAI provides Lean files for this family: lean/docs/135.md. The Lean statements have not been checked by people against the paper's claims.

Family 135: Homogeneous depth-five lower bounds for iterated matrix multiplication

Over every characteristic-zero field, the $(1,1)$ entry of a product of n independent $n\times n$ variable matrices requires $n^{\Theta(\sqrt n)}$ gates in homogeneous depth-five sum–product circuits. This sharp bound allows shared gates and bottom linear forms involving all variables.

This is the only paper in this family.