BaKron Cuts Two-Sided Kronecker-Hessian Quantization From O(m²n²) to O(mn(m+n)), Matching GPTQ's Scaling

arXiv 2608.06291·low signalXBlueskyLinkedInCopy link

BaKron (arXiv 2608.06291, Aug 6) speeds up adaptive-rounding quantization that uses two-sided Kronecker-factored Hessian approximations — which capture correlations across output coordinates that GPTQ's one-sided activation-derived information misses, but are expensive in the vectorized weight domain. Combining anti-diagonal parallelism with a recursive divide-and-conquer construction, BaKron needs O(m+n) sequential steps for an m×n weight matrix and reduces total work from O(m²n²) to O(mn(m+n)), matching GPTQ's cubic scaling while exploiting richer curvature. It is modular with respect to both the base quantizer and the Hessian estimator, so it slots into existing quantization stacks rather than replacing them.