Bayesian inference with limited resources
How to do Bayesian inference with bounded computational resources?
- Limited resources: finite automata, polynomial time, etc.
- Fundamental limits: undecidability
A possible application that interests me is Bayesian inference in automated theorem proving or computer algebra.
Literature
- Wilson, 2014: Bounded information and biases in information processing (doi)
- Original manuscript in 2002 (pdf)
- Halpern, Pass, Seeman, 2014: Decision theory with resource-bounded agents (arxiv, doi)
- Ackerman, Freer, Roy, 2011: On the computability of conditional probability
(arxiv)
- Talk at Simons Institute workshop on Uncertainty in Computation (2016)
- Related MO answer