Hot eventLive
QSS论文:基于量化充分统计量的精确机器遗忘
1 reports1 sources3 hr ago updated
Get the story
AI overview
2026年10月7日,arXiv · Machine Learning Theory(一手)发表关于Quantized Sufficient Statistics(QSS)实现精确机器遗忘的论文。QSS将小型冻结schema与可变的求和可分解内容分离,删除内容时只需精确减法而非优化。其变体QSS-L可精确移除标签但保留未标注输入;QSS-E则通过不学习可删除样本,同时移除输入与标签。目前公开信息仅涉及该论文方法描述,尚无后续实验验证或第三方评论。
Generated from reports · updated 3 hr ago
Timeline
Follow the coverage from different angles.
Oct 7, 2026
- arXiv · Machine Learning TheoryQuantized Sufficient Statistics 实现精确机器遗忘
Quantized Sufficient Statistics(QSS)把小型冻结 schema 与可变的求和可分解内容分离,删除内容只需精确减法而非优化。QSS-L 精确移除标签但保留未标注输入,QSS-E 则通过不学习可删除样本来同时移除输入与标签。
Heat trend
Current heat 9·Comparable peak 10(Oct 7)·Comparable change over 24 hours –
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.