La prévision : ses lois logiques, ses sources subjectives

By B. D. Finetti. 1937

How researchers see this paper

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

Citations in the corpus

Neural Processes (2018, background): “This essentially corresponds to a conditional version of de Finetti’s Theorem that anchors much of Bayesian nonparametrics (De Finetti, 1937).”
Randomized Prior Functions for Deep Reinforcement Learning (2018, background): “Colloquially, this means that any decision rule that is not Bayesian can be improved (or even exploited) by some Bayesian alternative [14].”
Learning Bayesian networks: The combination of knowledge and statistical data (1994, background): “Given an exchangeable sequence, De Finetti (1937) showed that there exists parameters Oy = {0~=l , .”
Graph limits and exchangeable random graphs (2007, background): “The celebrated representation theorem says Theorem 1.1 (deFinetti) .”
Symmetry of models versus models of symmetry (2008, background): “56 As we shall see further on, this essentially simple result has many interesting consequences, amongst which a generalisation to coherent lower previsions of de Finetti’s [1937] representation result for finite sequences of exchangeable random variables (see Section 9.”
Objective and Subjective Rationality in a Multiple Prior Model (2010, background): “As mentioned above, the works of Ramsey (1931), de Finetti (1937), Savage (1954), and Anscombe and Aumann (1963) famously championed the Bayesian approach, suggesting that any uncertainty can be reduced to risk using the notion of subjective probabilities.”
Uncertainty Theory (2004, unknown): “The frequency interpretation takes the probability to be the frequency with which an event happens (Venn [146], Reichenbach [129], von Mises [147]), while the belief interpretation takes the probability to be the degree to which we believe an event will happen (Ramsey [128], de Finetti [23], Savage ”
When did Bayesian inference become "Bayesian"? (2006, background): “For example, de Finetti (43) in his 1950 Berkeley symposium paper refers to an abstract of a paper presented by Savage in 1949 at the Econometric Society meeting and, in it, Savage refers to de Finetti’s ideas, referencing de Finetti (42).”
A Generalization of Quantum Stein’s Lemma (2009, background): “There have been several interesting recent developments on quantum versions [20, 21, 59, 60] of the seminal result by Bruno de Finetti on the characterization of exchangeable probability distributions [61].”
Bernstein's inequalities for general Markov chains (2018, unknown): “Exchangeability, particularly useful in the analysis of large networks, relies on de Finetti’s theorem de Finetti (1937) and the Aldous-Hoover-Kallenberg approach (Aldous, 1981; Hoover, 1979; Kallenberg, 2005).”