Timezone: »

Spectral Learning from a Single Trajectory under Finite-State Policies
Borja de Balle Pigem · Odalric Maillard

Mon Aug 07 06:06 PM -- 06:24 PM (PDT) @ C4.4

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 i.i.d. 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.

Author Information

Borja de Balle Pigem (Amazon Research Cambridge)
Odalric Maillard

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors