PAC learning of Probabilistic Automaton ...
Document type :
Communication dans un congrès avec actes
Title :
PAC learning of Probabilistic Automaton based on the Method of Moments
Author(s) :
Glaude, Hadrien [Auteur]
Université de Lille, Sciences et Technologies
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Sequential Learning [SEQUEL]
Thales Airborne Systems
Pietquin, Olivier [Auteur]
Institut universitaire de France [IUF]
Université de Lille, Sciences et Technologies
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Sequential Learning [SEQUEL]
Université de Lille, Sciences et Technologies
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Sequential Learning [SEQUEL]
Thales Airborne Systems
Pietquin, Olivier [Auteur]
Institut universitaire de France [IUF]
Université de Lille, Sciences et Technologies
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Sequential Learning [SEQUEL]
Conference title :
International Conference on Machine Learning (ICML 2016)
City :
New York
Country :
Etats-Unis d'Amérique
Start date of the conference :
2016-06-19
HAL domain(s) :
Informatique [cs]/Apprentissage [cs.LG]
English abstract : [en]
Probabilitic Finite Automata (PFA) are gener-ative graphical models that define distributions with latent variables over finite sequences of symbols, a.k.a. stochastic languages. Traditionally , unsupervised learning of ...
Show more >Probabilitic Finite Automata (PFA) are gener-ative graphical models that define distributions with latent variables over finite sequences of symbols, a.k.a. stochastic languages. Traditionally , unsupervised learning of PFA is performed through algorithms that iteratively improves the likelihood like the Expectation-Maximization (EM) algorithm. Recently, learning algorithms based on the so-called Method of Moments (MoM) have been proposed as a much faster alternative that comes with PAC-style guarantees. However, these algorithms do not ensure the learnt automata to model a proper distribution , limiting their applicability and preventing them to serve as an initialization to iterative algorithms. In this paper, we propose a new MoM-based algorithm with PAC-style guarantees that learns automata defining proper distributions. We assess its performances on synthetic problems from the PAutomaC challenge and real datasets extracted from Wikipedia against previous MoM-based algorithms and EM algorithm.Show less >
Show more >Probabilitic Finite Automata (PFA) are gener-ative graphical models that define distributions with latent variables over finite sequences of symbols, a.k.a. stochastic languages. Traditionally , unsupervised learning of PFA is performed through algorithms that iteratively improves the likelihood like the Expectation-Maximization (EM) algorithm. Recently, learning algorithms based on the so-called Method of Moments (MoM) have been proposed as a much faster alternative that comes with PAC-style guarantees. However, these algorithms do not ensure the learnt automata to model a proper distribution , limiting their applicability and preventing them to serve as an initialization to iterative algorithms. In this paper, we propose a new MoM-based algorithm with PAC-style guarantees that learns automata defining proper distributions. We assess its performances on synthetic problems from the PAutomaC challenge and real datasets extracted from Wikipedia against previous MoM-based algorithms and EM algorithm.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- https://hal.inria.fr/hal-01406889/document
- Open access
- Access the document
- https://hal.inria.fr/hal-01406889/document
- Open access
- Access the document
- document
- Open access
- Access the document
- glaude16.pdf
- Open access
- Access the document
- document
- Open access
- Access the document
- glaude16.pdf
- Open access
- Access the document