Skip to content
Hot eventLive

复合在线到非凸转换达最优Oracle复杂度

1 reports1 sources3 hr ago updated

Get the story

AI overview

2026年10月9日，arXiv（Statistics Machine Learning）发布论文，针对随机非光滑非凸复合优化问题，提出扩展的 online-to-nonconvex conversion 框架。该框架引入包含正则项本身而非其线性化的新损失，并采用 online mirror descent 变体以获得低遗憾，从而实现最优 Oracle 复杂度。这是该事件目前唯一报道，尚未见后续验证或同行评议信息。

Generated from reports · updated 3 hr ago

LatestOct 9
论文提出含正则项本身的新损失与OMD变体，扩展在线到非凸转换框架。

Timeline

Follow the coverage from different angles.

Oct 9, 2026
  1. arXiv · Statistics Machine Learning
    复合在线到非凸转换达到最优 Oracle 复杂度

    论文针对随机非光滑非凸复合优化问题，提出扩展 online-to-nonconvex conversion 框架，引入包含正则项本身而非其线性化的新损失，并用 online mirror descent 变体获得低遗憾。

Heat trend

Current heat 9·Comparable peak 10（Oct 9）·Comparable change over 24 hours –

02.557.510Oct9Oct9Oct9Oct9

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.