Regret vs. Bandwidth Trade-off for Recommendation Systems

2018/10/15 by Linqi Song, Song, Linqi, Christina Fragouli +3
Computer Science · Decision Sciences · Engineering · #Advanced Bandit Algorithms Research #Advanced Wireless Network Optimization #Cognitive Radio Networks and Spectrum Sensing #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1810.06313

openalex publication_date 2018/10/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Efficient Learning in Large-Scale Combinatorial Semi-Bandits

Related

• Making recommendations bandwidth aware
• Online Learning to Cache and Recommend in the Next Generation Cellular Networks
• Regret in Online Recommendation Systems
• The Nah Bandit: Modeling User Non-compliance in Recommendation Systems
• HyperBandit: Contextual Bandit with Hypernewtork for Time-Varying User Preferences in Streaming Recommendation