Spectral Learning from a Single Trajectory under Finite-State Policies - Archive ouverte HAL Access content directly
Conference Papers Year : 2017

Spectral Learning from a Single Trajectory under Finite-State Policies

Abstract

We present spectral methods of moments for learning sequential models from a single trajec-tory, in stark contrast with the classical literature that assumes the availability of multiple i.i.d. trajectories. Our approach leverages an efficient SVD-based learning algorithm for weighted au-tomata and provides the first rigorous analysis for learning many important models using dependent data. We state and analyze the algorithm under three increasingly difficult scenarios: proba-bilistic automata, stochastic weighted automata, and reactive predictive state representations controlled by a finite-state policy. Our proofs include novel tools for studying mixing properties of stochastic weighted automata.
Fichier principal
Vignette du fichier
cr_ICML_HankelMatrices2.pdf (455.98 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01590940 , version 1 (20-09-2017)

Identifiers

  • HAL Id : hal-01590940 , version 1

Cite

Borja Balle, Odalric-Ambrym Maillard. Spectral Learning from a Single Trajectory under Finite-State Policies. International conference on Machine Learning, Jul 2017, Sidney, France. ⟨hal-01590940⟩
450 View
146 Download

Share

Gmail Facebook X LinkedIn More