2 papers
cs.IR2026
Massive Memorization with Hundreds of Trillions of Parameters for Sequential Transducer Generative Recommenders
Zhimin Chen, Chenyu Zhao, Ka Chun Mo +7
Modern large-scale recommendation systems rely heavily on user interaction history sequences to enhance the model performance. The advent of large language models and sequential mo…
stat.ML2025
Limits To (Machine) Learning
Zhimin Chen, Bryan Kelly, Semyon Malamud
Machine learning (ML) methods are highly flexible, but their ability to approximate the true data-generating process is fundamentally constrained by finite samples. We characterize…