Bayesian methods outperform classical ones on prediction error in correlated weak-signal settings, with Horseshoe providing near-nominal coverage and Lasso tying Spike-and-Slab on variable selection F1 score.
The No-U-Turn sampler: adaptively setting path lengths in Hamiltonian Monte Carlo.Journal of Machine Learning Research, 15(1): 1593–1623
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Sparse Regression under Correlation and Weak Signals: A Reproducible Benchmark of Classical and Bayesian Methods
Bayesian methods outperform classical ones on prediction error in correlated weak-signal settings, with Horseshoe providing near-nominal coverage and Lasso tying Spike-and-Slab on variable selection F1 score.