Pseudo-Mallows for Efficient Probabilistic Preference Learning

ORID fotqwXEglz · tags icml2026-repro paper-fotqwXEglz

#StatusPageArtifactClaim excerpt
1VERIFIED 2/201-pseudo-mallows-distribution-provides-closed-formartifactThe Pseudo-Mallows distribution provides a closed-form variational approximation…
2VERIFIED 2/202-optimal-ordering-v-set-used-factorizeartifactThe optimal ordering (V-set) used to factorize the Pseudo-Mallows distribution i…
3VERIFIED 2/203-small-item-sets-full-enumerationartifactFor small item sets (n ≤ 9), full enumeration shows that 'V'-shaped orderings mi…
4VERIFIED 2/204-number-observed-rankings-ranking-inducedartifactTheorem 2 shows that as the number of observed rankings N → ∞, the ranking induc…
5VERIFIED 2/205-algorithm-iterated-search-hungarian-methodartifactAlgorithm 2, an iterated search using the Hungarian Method for bipartite matchin…
6VERIFIED 2/206-pseudo-mallows-framework-extended-clicking-impliartifactThe Pseudo-Mallows framework is extended to clicking/implicit-feedback data and …

Open logbook index · logbook.json