SSLA approximates the posterior predictive distribution by refitting Bayesian models on self-predicted data, yielding a deterministic uncertainty measure that outperforms standard Laplace approximations in calibration on regression tasks.
Benchmarking B ayesian neural networks and evaluation metrics for regression tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
No citing papers match the current filters.