Latest

Theoretical computer science

Homogeneous depth-five lower bounds for iterated matrix multiplication

OpenAI research collection · 1 manuscript · Source checked 2026-10-19

OpenAI's result summary

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

Read the manuscripts

Short excerpts below come from OpenAI's abstracts. The full abstract and original PDF preserve the paper's precise scope.

MANUSCRIPT 01

Homogeneous depth-five lower bounds for iterated matrix multiplication

Let \mathop{IMM}\nolimits _{n,n} be the (1,1) entry of a product of n independent n× n matrices of variables. Over every field of characteristic zero, every syntactically homogeneous \Sigma\Pi\Sigma\Pi\Sigma circuit computing \mathop{IMM}\nolimits _{n,n} has at least n^{\sqrt n/400} gates for all sufficiently large n, with an…

Full source abstract

Let \mathop{IMM}\nolimits _{n,n} be the (1,1) entry of a product of n independent n× n matrices of variables. Over every field of characteristic zero, every syntactically homogeneous \Sigma\Pi\Sigma\Pi\Sigma circuit computing \mathop{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^{Θ(\sqrt n)}.

This exact PDF is not listed in the imported formalization catalogue. Family scope notes may contain further information.

One signal in the wider AGI picture

New mathematical reasoning could help AI tackle harder scientific and computational problems. How reliably these skills transfer beyond mathematics will determine how much they contribute to general intelligence.

Explore the AGI Clock ↗