TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

research

Two-Sided Curvature Lost a Power of Work

BaKron keeps Kronecker-factored Hessian information while reducing adaptive-rounding cost.

Published Updated Story ID: mp-2026-08-07-016
Read the complete editionStory JSON

Summary

BaKron keeps Kronecker-factored Hessian information while reducing adaptive-rounding cost.

For an m-by-n weight matrix, BaKron reduces total work from O(m^2 n^2) to O(mn(m+n)) with O(m+n) sequential steps, matching GPTQ's cubic scaling while retaining richer two-sided curvature information.

Why it matters

BaKron keeps Kronecker-factored Hessian information while reducing adaptive-rounding cost.

Limits and context

No additional limitation was separately recorded.

Key claims

  1. BaKron keeps Kronecker-factored Hessian information while reducing adaptive-rounding cost.

    Evidence: source-2026-08-07-018

Sources

  1. arXiv preprint 2608.06291arXiv · primary research

Corrections

No corrections have been recorded for this story.