一作ACL 2026Poster· Natural Language Processing
Fast and Accurate Fisher-Guided Quantization via Efficient Kronecker Factorization
Viktoriia A. Chekalina · Gerasin Timofey · Andrey Kuznetsov · Evgeny Frolov
摘要
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 t...