Casting top-K retrieval as an MDP over implicit-ALS posteriors with closed-form fold-in transitions, the paper reports that dynamics-aware planning (especially one-step lookahead) outperforms static top-K on multiple datasets under leave-last-n splits when using cosine similarity.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Planning over Matrix-Factorization MDPs for Candidate Generation
Casting top-K retrieval as an MDP over implicit-ALS posteriors with closed-form fold-in transitions, the paper reports that dynamics-aware planning (especially one-step lookahead) outperforms static top-K on multiple datasets under leave-last-n splits when using cosine similarity.