Spectral Learning from a Single Trajectory under Finite-State Policies

Authors: Borja Balle, Odalric-Ambrym Maillard

ICML 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical 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... Our proofs include novel tools for studying mixing properties of stochastic weighted automata.
Researcher Affiliation Collaboration 1Amazon Research, Cambridge, UK (work done at Lancaster University) 2Inria Lille Nord Europe, Villeneuve d Ascq, France.
Pseudocode Yes Algorithm 1: Spectral Learning for WFA
Open Source Code No The paper does not provide an explicit statement about releasing source code or a link to a code repository.
Open Datasets No The paper discusses learning from data ('a single trajectory') but does not specify a publicly available dataset by name or provide access information (link, DOI, or formal citation).
Dataset Splits No The paper focuses on theoretical analysis and algorithm design, and does not provide specific details on dataset splits (e.g., training, validation, test percentages or counts).
Hardware Specification No The paper is theoretical and does not describe any specific hardware used for experiments.
Software Dependencies No The paper is theoretical and does not list any software dependencies with specific version numbers.
Experiment Setup No The paper focuses on theoretical analysis and algorithm design, and does not provide specific experimental setup details such as hyperparameter values or training configurations.