Provably Data-driven Multiple Hyper-parameter Tuning with Structured Loss Function

ORID JnuwpwbZ8D · tags icml2026-repro paper-JnuwpwbZ8D

#StatusPageArtifactClaim excerpt
1VERIFIED 2/201-establishes-general-first-order-logic-frameworkartifactTheorem 4.1 establishes a general first-order-logic framework giving pseudo-dime…
2VERIFIED 2/202-bounds-pseudo-dimension-piecewise-polynomial-traartifactTheorem 5.1 bounds the pseudo-dimension of piecewise-polynomial training-loss ob…
3VERIFIED 2/203-extends-framework-bi-level-validation-loss-settiartifactTheorem 6.1 extends the framework to the bi-level validation-loss setting (f not…
4VERIFIED 2/204-optimal-parameter-path-theta-alphaartifactTheorem 7.2 shows that when the optimal parameter path theta*(x, alpha) is piece…
5VERIFIED 2/205-provides-first-learnability-guarantee-weightedartifactTheorem 8.1 provides the first learnability guarantee for weighted group LASSO r…
6VERIFIED 2/206-derives-pdim-bound-weighted-fusedartifactTheorem 8.2 derives a Pdim(L) = O(d^2) bound for weighted fused LASSO applied to…

Open logbook index · logbook.json