2 papers
cs.LG2024
Fully Heteroscedastic Count Regression with Deep Double Poisson Networks
Spencer Young, Porter Jenkins, Longchao Da +2
Neural networks capable of accurate, input-conditional uncertainty representation are essential for real-world AI systems. Deep ensembles of Gaussian networks have proven highly ef…
cs.LG2024
Assessing the Probabilistic Fit of Neural Regressors via Conditional Congruence
Spencer Young, Riley Sinema, Cole Edgren +3
While significant progress has been made in specifying neural networks capable of representing uncertainty, deep networks still often suffer from overconfidence and misaligned pred…