Using Time-Series Privileged Information for Provably Efficient Learning of Prediction Models
Paper i proceeding, 2022

We study prediction of future outcomes with supervised models that use privileged information during learning. The privileged information comprises samples of time series observed between the baseline time of prediction and the future outcome; this information is only available at training time which differs from the traditional supervised learning. Our question is when using this privileged data leads to more sample-efficient learning of models that use only baseline data for predictions at test time. We give an algorithm for this setting and prove that when the time series are drawn from a non-stationary Gaussian-linear dynamical system of fixed horizon, learning with privileged information is more efficient than learning without it. On synthetic data, we test the limits of our algorithm and theory, both when our assumptions hold and when they are violated. On three diverse real-world datasets, we show that our approach is generally preferable to classical learning, particularly when data is scarce. Finally, we relate our estimator to a distillation approach both theoretically and empirically. [GRAPHICS] .

Författare

Rickard K. A. Karlsson

TU Delft

Martin Willbo

RISE Research Institutes of Sweden

Zeshan Hussain

Massachusetts Institute of Technology (MIT)

Rahul G. Krishnan

University of Toronto

David Sontag

Massachusetts Institute of Technology (MIT)

Fredrik Johansson

Chalmers, Data- och informationsteknik, Data Science och AI

Proceedings of Machine Learning Research

26403498 (eISSN)

Vol. 151 5459-5484

International Conference on Artificial Intelligence and Statistics
virtual, ,

WASP AI/MLX Forskarassistent

Wallenberg AI, Autonomous Systems and Software Program, 2019-08-01 -- 2023-08-01.

Ämneskategorier

Annan data- och informationsvetenskap

Sannolikhetsteori och statistik

Mer information

Senast uppdaterat

2023-07-19