paper-with-me

홈 › Papers

Rank-Induced PL Mirror Descent: A Rank-Faithful Second-Order Algorithm for Sleeping Experts

2025-09-14 · Tiantian Zhang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.18138

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Implicit Regularization in Matrix Sensing via Mirror Descent

2021-05-28 · NeurIPS 2021 12 · Fan Wu, Patrick Rebeschini

We study discrete-time mirror descent applied to the unregularized empirical risk in matrix sensing. In both the general case of rectangular matrices and the particular case of positive semidefinite matrices, a simple po…

The Information Geometry of Mirror Descent

2013-10-29 · Garvesh Raskutti, Sayan Mukherjee

Information geometry applies concepts in differential geometry to probability and statistics and is especially useful for parameter estimation in exponential families where parameters are known to lie on a Riemannian man…

parameter estimation

Efficient randomized algorithms for PageRank problem

2016-05-26 · Gasnikov Alexander, Dmitriev Denis

In the paper we compare well known numerical methods of finding PageRank vector. We propose Markov Chain Monte Carlo method and obtain a new estimation for this method. We also propose a new method for PageRank problem b…

A Generalized Online Mirror Descent with Applications to Classification and Regression

2013-04-10 · Francesco Orabona, Koby Crammer, Nicolò Cesa-Bianchi

Online learning algorithms are fast, memory-efficient, easy to implement, and applicable to many prediction problems, including classification, regression, and ranking. Several online algorithms were proposed in the past…

General Classificationregression

A Mirror Descent Perspective of Smoothed Sign Descent

2024-10-18 · Shuyang Wang, Diego Klabjan

Recent work by Woodworth et al. (2020) shows that the optimization dynamics of gradient descent for overparameterized problems can be viewed as low-dimensional dual dynamics induced by a mirror map, explaining the implic…