Spectral learning from a single trajectory under finite-state policies
B Balle, OA Maillard - International Conference on Machine …, 2017 - proceedings.mlr.press
International Conference on Machine Learning, 2017•proceedings.mlr.press
We present spectral methods of moments for learning sequential models from a single
trajectory, in stark contrast with the classical literature that assumes the availability of
multiple iid trajectories. Our approach leverages an efficient SVD-based learning algorithm
for weighted automata 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: probabilistic automata, stochastic weighted automata, and reactive …
trajectory, in stark contrast with the classical literature that assumes the availability of
multiple iid trajectories. Our approach leverages an efficient SVD-based learning algorithm
for weighted automata 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: probabilistic automata, stochastic weighted automata, and reactive …
Abstract
We present spectral methods of moments for learning sequential models from a single trajectory, in stark contrast with the classical literature that assumes the availability of multiple iid trajectories. Our approach leverages an efficient SVD-based learning algorithm for weighted automata 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: probabilistic 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.
proceedings.mlr.press
Showing the best result for this search. See all results