English

Learning from many trajectories

Machine Learning 2023-02-01 v2 Machine Learning

Abstract

We initiate a study of supervised learning from many independent sequences ("trajectories") of non-independent covariates, reflecting tasks in sequence modeling, control, and reinforcement learning. Conceptually, our multi-trajectory setup sits between two traditional settings in statistical learning theory: learning from independent examples and learning from a single auto-correlated sequence. Our conditions for efficient learning generalize the former setting--trajectories must be non-degenerate in ways that extend standard requirements for independent examples. Notably, we do not require that trajectories be ergodic, long, nor strictly stable. For linear least-squares regression, given nn-dimensional examples produced by mm trajectories, each of length TT, we observe a notable change in statistical efficiency as the number of trajectories increases from a few (namely mnm \lesssim n) to many (namely mnm \gtrsim n). Specifically, we establish that the worst-case error rate of this problem is Θ(n/mT)\Theta(n / m T) whenever mnm \gtrsim n. Meanwhile, when mnm \lesssim n, we establish a (sharp) lower bound of Ω(n2/m2T)\Omega(n^2 / m^2 T) on the worst-case error rate, realized by a simple, marginally unstable linear dynamical system. A key upshot is that, in domains where trajectories regularly reset, the error rate eventually behaves as if all of the examples were independent, drawn from their marginals. As a corollary of our analysis, we also improve guarantees for the linear system identification problem.

Keywords

Cite

@article{arxiv.2203.17193,
  title  = {Learning from many trajectories},
  author = {Stephen Tu and Roy Frostig and Mahdi Soltanolkotabi},
  journal= {arXiv preprint arXiv:2203.17193},
  year   = {2023}
}
R2 v1 2026-06-24T10:33:39.666Z