Conceptlikelihood tempering / 温度调节

Likelihood Temperature Scaling

A technique used in Bayesian inference that applies a temperature parameter T to the likelihood function, equivalently adjusting the weight of the KL divergence term in the ELBO. This balances the relative strength of data fitting against prior regularization.

Timeline (last 90 days)

Oct 8

Likelihood temperature scaling raises the likelihood function to the power of 1/T (T < 1), which is equivalent to multiplying the KL term in the ELBO by a coefficient T.

Unverified50%

All Facts (1)

Unverified

Likelihood temperature scaling raises the likelihood function to the power of 1/T (T < 1), which is equivalent to multiplying the KL term in the ELBO by a coefficient T.

50%

Source Articles

How Likelihood Tempering Rescues Bayesian Neural Networks from 'Prior Collapse'Oct 8