Gradient flow of the stochastic relaxation on a generic exponential family

Journal Article · Tue Jan 13 00:00:00 EST 2015 · AIP Conference Proceedings

DOI:https://doi.org/10.1063/1.4905998· OSTI ID:22390868

Malagò, Luigi ^[1]; Pistone, Giovanni ^[2]

---

1. Collegio Carlo Alberto, Via Real Collegio 30, 10024 Moncalieri, Italy and Shinshu University, 4-17-1 Wakasato, Nagano 380-8553 (Japan)
2. Collegio Carlo Alberto, Via Real Collegio 30, 10024 Moncalieri (Italy)

We study the natural gradient flow of the expected value E{sub p} [f] of an objective function f for p in an exponential family. We parameterize the exponential family with the expectation parameters and we show that the dynamical system associated to the natural gradient flow can be extended outside the marginal polytope.

• OSTI ID: 22390868
• Journal Information: AIP Conference Proceedings, Vol. 1641, Issue 1; Conference: MAXENT 2014: Conference on Bayesian Inference and Maximum Entropy Methods in Science and Engineering, Clos Luce, Amboise (France), 21-26 Sep 2014; Other Information: (c) 2015 AIP Publishing LLC; Country of input: International Atomic Energy Agency (IAEA); ISSN 0094-243X
• Country of Publication: United States
• Language: English

Related Subjects

71 CLASSICAL AND QUANTUM MECHANICS
GENERAL PHYSICS
EXPECTATION VALUE
FUNCTIONS
PARAMETRIC ANALYSIS
RELAXATION
STOCHASTIC PROCESSES