Unverified50% confidenceFactExact time
About a year later (around 2016), Santambrogio proved the same result using a variational problem over probability distributions, where the functional's first term is entropy and the second term comes from the dual problem of optimal transport.
1
Sources
50%
Confidence
Long-term
Relevance
9/21/2026
First Seen
Sources
Related Entities
Related Claims
Unverified线性回归的最小二乘损失与逻辑回归的交叉熵损失分别对应高斯噪声假设与伯努利分布假设下的最大似然估计65% similarUnverifiedAssuming the data follows a Bernoulli or multinomial distribution, maximizing the likelihood is equivalent to minimizing the cross-entropy loss function.64% similarUnverifiedFinite-sample estimation of entropy rate faces a systematic negative bias problem, where plug-in estimators tend to underestimate the true entropy; this can be compensated using the Miller-Madow correction by adding a (k-1)/(2N) term.61% similarUnverifiedMinimizing cross-entropy is equivalent to minimizing the KL divergence between the true distribution and the predicted distribution.61% similarUnverifiedPerplexity equals the exponential of the cross-entropy loss on the test set: PPL = exp(loss), where loss=1.77 corresponds to PPL≈5.86.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/937736API
curl https://kongchang.com/api/v1/knowledge/claims/937736MCP
get_claim(id=937736)