VD-LARS performs exact T-Rex-style FDR-controlled selection in high dimensions by adaptively sampling dummy projections via stick-breaking, preserving selection laws and guarantees while cutting memory and runtime by orders of magnitude.
For this ω, the weights q(nrs)(ω) are deterministic, satisfyP j(q(nrs) j (ω))2 = 1 and maxj |q(nrs) j (ω)| →0
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Virtual Dummies: Enabling Scalable FDR-Controlled Variable Selection via Sequential Sampling of Null Features
VD-LARS performs exact T-Rex-style FDR-controlled selection in high dimensions by adaptively sampling dummy projections via stick-breaking, preserving selection laws and guarantees while cutting memory and runtime by orders of magnitude.