EXCHANGEABILITY, PREDICTIVE DISTRIBUTIONS AND PARAMETRIC MODELS*

By S. Fortini, L. Bocconi, L. Ladelli, E. Regazzini. 2000

67 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/163e74335bdbafe065c7733ceec9db4b10bbfc60

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Christopher C. Holmes
2. Edwin Fong
3. Benjamin Bloem-Reddy
4. Stephen G. Walker
5. Yee Whye Teh
6. Michael I. Jordan
7. Yoshua Bengio
8. David M. Blei

Citations in the corpus

• Martingale posterior distributions (2021, background): “Fortini et al. (2000) investigate under what conditions parametric models arise from the sequence of predictives using the concept of predictive sufficiency, and derive conditions such that the joint distribution is exchangeable.”
• Probabilistic Symmetries and Invariant Neural Networks (2020, background): “When Y is the prediction of Xn+1 from Xn, adequacy is also known as predictive sufficiency (Fortini et al., 2000) and, under certain conditions, it is equivalent to sufficiency and transitivity (Bahadur, 1954) or to total sufficiency (Lauritzen, 1974a).”