Appeared at: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2022Authors: Sambhav Solanki, Sujit Gujar, Sankarshan Damle, Samhita Kanaparthy In multi-agent online learning settings, federated learning (FL) is a valuable tool. However, the learning agents can be competitive, and privacy concerns can pose a barrier to engagement in FL. … Continue reading Differentially Private Federated Combinatorial Bandits with Constraints
Designing Truthful Contextual Multi-Armed Bandits based Sponsored Search Auctions
In this work, we consider the contextual multi-armed bandit problem in the presence of strategic agents in the context of sponsored search auction. In this setting, an advertising platform (center) runs a repeated auction to select the best-suited ads relevant to the user’s query. The center aspires to select an ad that has a high … Continue reading Designing Truthful Contextual Multi-Armed Bandits based Sponsored Search Auctions