Papers › Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent

Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent

5 Nov 2020NeurIPS 2020 12arXiv:2011.02817archive 2025-07-28

Dimitris Fotakis, Thanasis Lianeas, Georgios Piliouras, Stratis Skoulakis

We consider a natural model of online preference aggregation, where sets of preferred items R₁, R₂, …, Rₜ along with a demand for kₜ items in each Rₜ, appear online. Without prior knowledge of (Rₜ, kₜ), the learner maintains a ranking πₜ aiming that at least kₜ items from Rₜ appear high in πₜ. This is a fundamental problem in preference aggregation with applications to, e.g., ordering product or news items in web pages based on user scrolling and click patterns. The widely studied Generalized Min-Sum-Set-Cover (GMSSC) problem serves as a formal model for the setting above. GMSSC is NP-hard and the standard application of no-regret online learning algorithms is computationally inefficient, because they operate in the space of rankings. In this work, we show how to achieve low regret for GMSSC in polynomial-time. We employ dimensionality reduction from rankings to the space of doubly stochastic matrices, where we apply Online Gradient Descent. A key step is to show how subgradients can be computed efficiently, by solving the dual of a configuration LP. Using oblivious deterministic and randomized rounding schemes, we map doubly stochastic matrices back to rankings with a small loss in the GMSSC objective.

PaperPDFConference PDFCode

Code

sskoul/ID2216 officialmentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Dimensionality Reduction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections