System Identification via Meta-Learning in Linear Time-Varying Environments

10/27/2020
by   Sen Lin, et al.
0

System identification is a fundamental problem in reinforcement learning, control theory and signal processing, and the non-asymptotic analysis of the corresponding sample complexity is challenging and elusive, even for linear time-varying (LTV) systems. To tackle this challenge, we develop an episodic block model for the LTV system where the model parameters remain constant within each block but change from block to block. Based on the observation that the model parameters across different blocks are related, we treat each episodic block as a learning task and then run meta-learning over many blocks for system identification, using two steps, namely offline meta-learning and online adaptation. We carry out a comprehensive non-asymptotic analysis of the performance of meta-learning based system identification. To deal with the technical challenges rooted in the sample correlation and small sample sizes in each block, we devise a new two-scale martingale small-ball approach for offline meta-learning, for arbitrary model correlation structure across blocks. We then quantify the finite time error of online adaptation by leveraging recent advances in linear stochastic approximation with correlated samples.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/18/2019

Continuous Meta-Learning without Tasks

Meta-learning is a promising strategy for learning to efficiently learn ...
research
04/17/2020

A Comprehensive Overview and Survey of Recent Advances in Meta-Learning

This article reviews meta-learning which seeks rapid and accurate model ...
research
02/25/2020

A Sample Complexity Separation between Non-Convex and Convex Meta-Learning

One popular trend in meta-learning is to learn from many training tasks ...
research
12/04/2019

Learning to Recommend via Meta Parameter Partition

In this paper we propose to solve an important problem in recommendation...
research
01/22/2022

FALCON: Fast and Accurate Multipath Scheduling using Offline and Online Learning

Multipath transport protocols enable the concurrent use of different net...
research
02/27/2018

Identification of LTV Dynamical Models with Smooth or Discontinuous Time Evolution by means of Convex Optimization

We establish a connection between trend filtering and system identificat...
research
02/10/2020

Compositional ADAM: An Adaptive Compositional Solver

In this paper, we present C-ADAM, the first adaptive solver for composit...

Please sign up or login with your details

Forgot password? Click here to reset