SPSC recovers drifting low-rank subspaces from scalar rewards under known noise variance, bounded coupling, and full probe support, then achieves dynamic regret scaling as r sqrt(T) plus lower-order terms instead of d sqrt(T).
arXiv preprint arXiv:2509.05460 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Variations in user state embeddings for CMAB recommenders can improve performance more than changing the bandit algorithm, with no embedding or aggregation strategy dominating across datasets.
citing papers explorer
-
Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity
SPSC recovers drifting low-rank subspaces from scalar rewards under known noise variance, bounded coupling, and full probe support, then achieves dynamic regret scaling as r sqrt(T) plus lower-order terms instead of d sqrt(T).
-
The Bandit's Blind Spot: The Critical Role of User State Representation in Recommender Systems
Variations in user state embeddings for CMAB recommenders can improve performance more than changing the bandit algorithm, with no embedding or aggregation strategy dominating across datasets.