Learning-Augmented Moment Estimation on Time-Decay Models
This work addresses the problem of efficient data processing for applications with unequal item weights, such as those subject to privacy regulation laws, providing a solution for data analysts and scientists working with time-decay models.
This paper tackles the problem of moment estimation in time-decay models, achieving improved space efficiency through learning-augmented algorithms, with results demonstrated on real and synthetic datasets. The paper presents algorithms for various fundamental problems, including norm and frequency estimation.
Motivated by the prevalence and success of machine learning, a line of recent work has studied learning-augmented algorithms in the streaming model. These results have shown that for natural and practical oracles implemented with machine learning models, we can obtain streaming algorithms with improved space efficiency that are otherwise provably impossible. On the other hand, our understanding is much more limited when items are weighted unequally, for example, in the sliding-window model, where older data must be expunged from the dataset, e.g., by privacy regulation laws. In this paper, we utilize an oracle for the heavy-hitters of datasets to give learning-augmented algorithms for a number of fundamental problems, such as norm/moment estimation, frequency estimation, cascaded norms, and rectangular moment estimation, in the time-decay setting. We complement our theoretical results with a number of empirical evaluations that demonstrate the practical efficiency of our algorithms on real and synthetic datasets.