Unverified50% confidenceFactExact time
Traditional rounding operations introduce errors of order α in the mean and χ² divergence of the privacy loss.
1
Sources
50%
Confidence
Long-term
Relevance
11/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe previously best differentially private online expert prediction algorithm had a regret bound of Õ(√T); when L* is much smaller than T, this bound is far higher than the non-private lower bound Õ(√L*).66% similarUnverified下游用户对模型的二次微调可能意外破坏原有安全特性65% similarUnverifiedFixed-cardinality sampling breaks independence across steps, and its privacy loss accounting cannot directly apply the decomposition formula of Poisson sampling, requiring special handling.63% similarVerifiedDifferential privacy mathematically guarantees that individual user behavior cannot be inferred from aggregated data by injecting calibrated noise into statistical results.63% similarUnverifiedRobust aggregation methods may misjudge legitimate updates from normal clients as anomalous under non-independent and identically distributed (non-IID) data, because differences in data distributions among clients themselves cause gradient directions to diverge.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1125653API
curl https://kongchang.com/api/v1/knowledge/claims/1125653MCP
get_claim(id=1125653)