Goto

Collaborating Authors

 conversion








GeneralizedDelayedFeedbackModel withPost-Click InformationinRecommenderSystems

Neural Information Processing Systems

However,accurate conversion labels arerevealed after along delay,which harms the timeliness ofrecommender systems. Previousliterature concentrates onutilizing early conversions to mitigate such a delayed feedback problem. In this paper, we show that post-click user behaviors are also informative to conversion rate prediction and can beused toimprovetimeliness.



RevisitingNeuralScalingLaws inLanguageandVision

Neural Information Processing Systems

The remarkable progress in deep learning in recent years is largely driven by improvements in scale, where bigger models are trained on larger datasets for longerschedules.