@inproceedings{chekalina-etal-2026-fast,
title = "Fast and Accurate Fisher-Guided Quantization via Efficient Kronecker Factorization",
author = "Chekalina, Viktoriia A. and
Timofey, Gerasin and
Kuznetsov, Andrey and
Frolov, Evgeny",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1805/",
pages = "38925--38935",
ISBN = "979-8-89176-390-6",
abstract = "Quantization has shown strong results in preserving model quality under compression. However, under aggressive bit-width reductions, even quantization may require additional information to prevent performance degradation. A natural source of it is second-order curvature information, captured by the Hessian. Since the Hessian of the model layers is prohibitively large, direct computation is infeasible, making structured parameterizations and approximations crucial in practice.In this work, we propose efficient Kronecker-factored approximation yielding state-of-the-art performance when integrated into existing quantization schemes. Evaluations on the LLaMA and Qwen model families show near-baseline quality at 4-bit compression and only a 5{--}6{\%} degradation at 2-bit. Moreover, our method substantially accelerates the most expensive component in second-order quantization {--} Hessian parameterization {--} achieving up to a 10{\texttimes} speedup over prior approaches."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chekalina-etal-2026-fast">
<titleInfo>
<title>Fast and Accurate Fisher-Guided Quantization via Efficient Kronecker Factorization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Viktoriia</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Chekalina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerasin</namePart>
<namePart type="family">Timofey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrey</namePart>
<namePart type="family">Kuznetsov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evgeny</namePart>
<namePart type="family">Frolov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Quantization has shown strong results in preserving model quality under compression. However, under aggressive bit-width reductions, even quantization may require additional information to prevent performance degradation. A natural source of it is second-order curvature information, captured by the Hessian. Since the Hessian of the model layers is prohibitively large, direct computation is infeasible, making structured parameterizations and approximations crucial in practice.In this work, we propose efficient Kronecker-factored approximation yielding state-of-the-art performance when integrated into existing quantization schemes. Evaluations on the LLaMA and Qwen model families show near-baseline quality at 4-bit compression and only a 5–6% degradation at 2-bit. Moreover, our method substantially accelerates the most expensive component in second-order quantization – Hessian parameterization – achieving up to a 10× speedup over prior approaches.</abstract>
<identifier type="citekey">chekalina-etal-2026-fast</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1805/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>38925</start>
<end>38935</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fast and Accurate Fisher-Guided Quantization via Efficient Kronecker Factorization
%A Chekalina, Viktoriia A.
%A Timofey, Gerasin
%A Kuznetsov, Andrey
%A Frolov, Evgeny
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F chekalina-etal-2026-fast
%X Quantization has shown strong results in preserving model quality under compression. However, under aggressive bit-width reductions, even quantization may require additional information to prevent performance degradation. A natural source of it is second-order curvature information, captured by the Hessian. Since the Hessian of the model layers is prohibitively large, direct computation is infeasible, making structured parameterizations and approximations crucial in practice.In this work, we propose efficient Kronecker-factored approximation yielding state-of-the-art performance when integrated into existing quantization schemes. Evaluations on the LLaMA and Qwen model families show near-baseline quality at 4-bit compression and only a 5–6% degradation at 2-bit. Moreover, our method substantially accelerates the most expensive component in second-order quantization – Hessian parameterization – achieving up to a 10× speedup over prior approaches.
%U https://aclanthology.org/2026.acl-long.1805/
%P 38925-38935
Markdown (Informal)
[Fast and Accurate Fisher-Guided Quantization via Efficient Kronecker Factorization](https://aclanthology.org/2026.acl-long.1805/) (Chekalina et al., ACL 2026)
ACL