Notabletraining methodsMiniMax

When and Why SignSGD Outperforms SGD: A Theoretical Study Based on ll_1-norm Lower Bounds

Hongyi Tao, Dingzhi Yu, Lijun Zhang

Published
May 7, 2026 17:32 UTC

Summarised from the primary source with AI assistance under human editorial oversight. Turing Wire is not a primary source — read the original for the authoritative account.

Source: arXiv cs.AI