A First Look at Rigorous Probability Theory
By Jeffrey S. Rosenthal. 2000
282 citations recorded by the source corpus.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/07651e2670a9e7a4a466f7a4b936275b1c07a0a6
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Amir-massoud Farahmand
- Sergey Levine
- Csaba Szepesvari
- Zoubin Ghahramani
- Yoshua Bengio
- Ruslan Salakhutdinov
- Pieter Abbeel
- Gareth O. Roberts
Citations in the corpus
- Practical probabilistic programming with monads (2015, background): “Measure theory is a vast subject and rather than trying to review it here, we refer the readers to general texts such as (Rosenthal 2006).”
- General state space Markov chains and MCMC algorithms (2004, background): “[13], Theorem 27.1; or [ 83 ], p. 110) will prove Theorem 24, provided that each term has finite second moment, and that the error term E(n) can be neglected.”
- Weak convergence of Metropolis algorithms for non-i.i.d. target distributions (2007, background): “, [15]), the term in brackets converges to biE[(f ′(X)/f(X))2].”
- Regularization in reinforcement learning (2011, methodology): “For more information about the RKHS-based approach to machine learning the reader is referred to the books by Schölkopf and Smola [2002]; Shawe-Taylor and Cristianini [2004]; Steinwart and Christmann [2008]. The main contributions of this work are as follows: First, we prove a relative deviation con”
- Measure Transformer Semantics for Bayesian Machine Learning (2011, background): “), as sugar for observe (x−y)). To give a formal semantics to such observations, as well as to mixtures of continuous and discrete distributions, we turn to measure theory, following standard sources [6, 48]. Two basic concepts are measurable spaces and measures. A measurable space is a set of value”