{"ID":2871417,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.18138","arxiv_id":"2509.18138","title":"Rank-Induced PL Mirror Descent: A Rank-Faithful Second-Order Algorithm for Sleeping Experts","abstract":"We introduce a new algorithm, \\emph{Rank-Induced Plackett--Luce Mirror Descent (RIPLM)}, which leverages the structural equivalence between the \\emph{rank benchmark} and the \\emph{distributional benchmark} established in \\citet{BergamOzcanHsu2022}. Unlike prior approaches that operate on expert identities, RIPLM updates directly in the \\emph{rank-induced Plackett--Luce (PL)} parameterization. This ensures that the algorithm's played distributions remain within the class of rank-induced distributions at every round, preserving the equivalence with the rank benchmark. To our knowledge, RIPLM is the first algorithm that is both (i) \\emph{rank-faithful} and (ii) \\emph{variance-adaptive} in the sleeping experts setting.","short_abstract":"We introduce a new algorithm, \\emph{Rank-Induced Plackett--Luce Mirror Descent (RIPLM)}, which leverages the structural equivalence between the \\emph{rank benchmark} and the \\emph{distributional benchmark} established in \\citet{BergamOzcanHsu2022}. Unlike prior approaches that operate on expert identities, RIPLM update...","url_abs":"https://arxiv.org/abs/2509.18138","url_pdf":"https://arxiv.org/pdf/2509.18138v1","authors":"[\"Tiantian Zhang\"]","published":"2025-09-14T18:16:05Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}