Efficient learning of nonlinear prediction models with time-series privileged information
Paper in proceeding, 2022

In domains where sample sizes are limited, efficient learning algorithms are critical. Learning using privileged information (LuPI) offers increased sample efficiency by allowing prediction models access to auxiliary information at training time which is unavailable when the models are used. In recent work, it was shown that for prediction in linear-Gaussian dynamical systems, a LuPI learner with access to intermediate time series data is never worse and often better in expectation than any unbiased classical learner. We provide new insights into this analysis and generalize it to nonlinear prediction tasks in latent dynamical systems, extending theoretical guarantees to the case where the map connecting latent variables and observations is known up to a linear transform. In addition, we propose algorithms based on random features and representation learning for the case when this map is unknown. A suite of empirical results confirm theoretical findings and show the potential of using privileged time-series information in nonlinear prediction.

Author

Bastian Jung

Student at Chalmers

Fredrik Johansson

Chalmers, Computer Science and Engineering (Chalmers), Data Science and AI

Advances in Neural Information Processing Systems

10495258 (ISSN)

Vol. 35
9781713871088 (ISBN)

36th Conference on Neural Information Processing Systems, NeurIPS 2022
New Orleans, USA,

Subject Categories

Probability Theory and Statistics

Computer Science

ISBN

9781713871088

More information

Latest update

1/15/2024