Unverified50% confidenceFactExact time
The theoretical foundations of empirical risk minimization can be traced back to the work of Vapnik and Chervonenkis in the 1970s, who proved that under conditions such as finite VC dimension of the hypothesis space, empirical risk minimizers can converge to true risk minimizers at a controllable rate.
1
Sources
50%
Confidence
Long-term
Relevance
9/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedVicinal Risk Minimization（VRM）理论由Chapelle等人在2001年提出，主张在训练样本的邻域上最小化风险73% similarUnverifiedResearchers have found that fine-tuning only a small number of model parameters is sufficient to remove safety alignment (de-alignment attacks), and that certain jailbreak prompts can transfer across different models.65% similarUnverified朴素贝叶斯中需要使用对数概率空间来规避连乘小概率值导致的下溢64% similarUnverifiedThe choice of bottleneck dimensionality is essentially a trade-off between information compression rate and reconstruction quality, corresponding to rate-distortion theory; Shannon proved in 1959 that there exists a theoretical minimum coding rate lower bound for a given distortion tolerance.63% similarUnverifiedSoftmax输出的概率值并不等同于真实的贝叶斯后验概率，而是被过度优化以拉开类别间距，导致预测概率系统性偏高61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/844875API
curl https://kongchang.com/api/v1/knowledge/claims/844875MCP
get_claim(id=844875)