站内快照 · 国内可打开。外网原文可能无法访问。

• 论文公开站arXiv2026年10月9日 22:12

  Rounding in Preconditioner Space: Redesigning 4-bit AdamW Optimizer-State Quantization

  Quantizing AdamW's optimizer states reduces persistent storage, but quantization errors propagate through the moment recurrences and perturb subsequent adaptive updates. We redesign 4-bit optimizer-state quantization for AdamW from the perspective of \emph{rounding space}: the co

  原文链接