arXiv:1810.06313 [cs.LG]AbstractReferencesReviewsResources
Regret vs. Bandwidth Trade-off for Recommendation Systems
Linqi Song, Christina Fragouli, Devavrat Shah
Published 2018-10-15Version 1
We consider recommendation systems that need to operate under wireless bandwidth constraints, measured as number of broadcast transmissions, and demonstrate a (tight for some instances) tradeoff between regret and bandwidth for two scenarios: the case of multi-armed bandit with context, and the case where there is a latent structure in the message space that we can exploit to reduce the learning phase.
Related articles: Most relevant | Search more
arXiv:1811.12591 [cs.LG] (Published 2018-11-30)
Active Learning in Recommendation Systems with Multi-level User Preferences
arXiv:2005.02435 [cs.LG] (Published 2020-05-05)
Effect of The Latent Structure on Clustering with GANs
arXiv:2012.02785 [cs.LG] (Published 2020-12-04)
Unsupervised embedding of trajectories captures the latent structure of mobility