8 papers
An analytical framework for the Levine hats problem: new strategies, bounds and generalizations
Clément Bouquet, Salah Chikhi, Timothé Charles +2
We study the Levine hat problem, a cooperative puzzle introduced by Lionel Levine in 2010, in which players must simultaneously identify a black hat on their own infinit…
Generalizing Linear Autoencoder Recommenders with Decoupled Expected Quadratic Loss
Ruixin Guo, Xinyu Li, Hao Zhou +2
Linear autoencoders (LAEs) have gained increasing popularity in recommender systems due to their simplicity and strong empirical performance. Most LAE models, including the Emphasi…
PAC-Bayes Bounds for Multivariate Linear Regression and Linear Autoencoders
Ruixin Guo, Ruoming Jin, Xinyu Li +1
Linear Autoencoders (LAEs) have shown strong performance in state-of-the-art recommender systems. However, this success remains largely empirical, with limited theoretical understa…
Efficient Federated Learning with Heterogeneous Data and Adaptive Dropout
Ji Liu, Beichen Ma, Qiaolin Yu +7
Federated Learning (FL) is a promising distributed machine learning approach that enables collaborative training of a global model using multiple edge devices. The data distributed…
Efficient Federated Learning with Timely Update Dissemination
Juncheng Jia, Ji Liu, Chao Huo +4
Federated Learning (FL) has emerged as a compelling methodology for the management of distributed data, marked by significant advancements in recent years. In this paper, we propos…
Learning Universal User Representations Leveraging Cross-domain User Intent at Snapchat
Clark Mingxuan Ju, Leonardo Neves, Bhuvesh Kumar +11
The development of powerful user representations is a key factor in the success of recommender systems (RecSys). Online platforms employ a range of RecSys techniques to personalize…