DeepAI AI Chat
Log In Sign Up

Learning from many trajectories

03/31/2022
by   Stephen Tu, et al.
0

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. They do not require that trajectories be ergodic, long, nor strictly stable. For linear least-squares regression, given n-dimensional examples produced by m trajectories, each of length T, we observe a notable change in statistical efficiency as the number of trajectories increases from a few (namely m ≲ n) to many (namely m ≳ n). Specifically, we establish that the worst-case error rate this problem is Θ(n / m T) whenever m ≳ n. Meanwhile, when m ≲ n, we establish a (sharp) lower bound of Ω(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 altogether, drawn from their marginals. As a corollary of our analysis, we also improve guarantees for the linear system identification problem.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/08/2018

New CleverHans Feature: Better Adversarial Robustness Evaluations with Attack Bundling

This technical report describes a new feature of the CleverHans library ...
03/24/2022

Learning the Dynamics of Autonomous Linear Systems From Multiple Trajectories

We consider the problem of learning the dynamics of autonomous linear sy...
06/16/2020

Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms

We study the problem of least squares linear regression where the data-p...
10/11/2021

Approximating Familywise Error Rate for Correlated Normal

We study the limiting behavior of the familywise error rate (FWER) of th...
04/09/2015

`local' vs. `global' parameters -- breaking the gaussian complexity barrier

We show that if F is a convex class of functions that is L-subgaussian, ...
03/17/2020

Finite-time Identification of Stable Linear Systems: Optimality of the Least-Squares Estimator

We provide a new finite-time analysis of the estimation error of stable ...
02/02/2019

Learning Linear Dynamical Systems with Semi-Parametric Least Squares

We analyze a simple prefiltered variation of the least squares estimator...