Epistemic Uncertainty
A type of uncertainty in machine learning uncertainty quantification that arises from insufficient knowledge of the true data-generating process. In theory, it can be reduced by adding more data.
Timeline (last 90 days)
A learner estimating the loss distribution from limited data inevitably has bias, causing the estimate of CVaR to deviate from the true value, thereby weakening or even reversing the actual effect of risk aversion.
The variance σ²(x) captures a mixture of epistemic uncertainty and aleatoric uncertainty, where the former reflects the model having seen little data and the latter reflects the inherent noise in the data itself.
All Facts (2)
A learner estimating the loss distribution from limited data inevitably has bias, causing the estimate of CVaR to deviate from the true value, thereby weakening or even reversing the actual effect of risk aversion.
50%UnverifiedThe variance σ²(x) captures a mixture of epistemic uncertainty and aleatoric uncertainty, where the former reflects the model having seen little data and the latter reflects the inherent noise in the data itself.
50%