arXiv subjects

Borja Balle

Publications and source records attributed to Borja Balle.

57 records · Page 4Linked to original sources

arXiv2015

A Canonical Form for Weighted Automata and Applications to Approximate Minimization

We study the problem of constructing approximations to a weighted automaton. Weighted finite automata (WFA) are closely related to the theory of rational series. A rational series is a function from strings to real numbers that can be computed by a finite WFA. Among others, this includes probability distributions generated by hidden Markov models and probabilistic automata. The relationship between rational series and WFA is analogous to the relationship between regular languages and ordinary automata. Associated with such rational series are infinite matrices called Hankel matrices which play a fundamental role in the theory of minimal WFA. Our contributions are: (1) an effective procedure for computing the singular value decomposition (SVD) of such infinite Hankel matrices based on their representation in terms of finite WFA; (2) a new canonical form for finite WFA based on this SVD decomposition; and, (3) an algorithm to construct approximate minimizations of a given WFA. The goal of our approximate minimization algorithm is to start from a minimal WFA and produce a smaller WFA that is close to the given one in a certain sense. The desired size of the approximating automaton is given as input. We give bounds describing how well the approximation emulates the behavior of the original WFA.

cs.FL↗

arXiv2013

Ergodicity of Random Walks on Random DFA

Given a DFA we consider the random walk that starts at the initial state and at each time step moves to a new state by taking a random transition from the current state. This paper shows that for typical DFA this random walk induces an ergodic Markov chain. The notion of typical DFA is formalized by showing that ergodicity holds with high probability when a DFA is sampled uniformly at random from the set of all automata with a fixed number of states. We also show the same result applies to DFA obtained by minimizing typical DFA.

cs.FL↗

arXiv2012

Local Loss Optimization in Operator Models: A New Insight into Spectral Learning

This paper re-visits the spectral method for learning latent variable models defined in terms of observable operators. We give a new perspective on the method, showing that operators can be recovered by minimizing a loss defined on a finite subset of the domain. A non-convex optimization similar to the spectral method is derived. We also propose a regularized convex relaxation of this optimization. We show that in practice the availabilty of a continuous regularization parameter (in contrast with the discrete number of states in the original method) allows a better trade-off between accuracy and model complexity. We also prove that in general, a randomized strategy for choosing the local loss will succeed with high probability.

cs.LG↗