A computational framework for Bayesian decision-making is developed and it is shown that as long as no action is optimal in every state, Bayes-optimal choice is intractable.
Abstract
We develop a computational framework for Bayesian decision-making. We show that as long as no action is optimal in every state, Bayes-optimal choice is intractable. This hardness need not arise from large action, state, or signal spaces, nor from a complicated represented utility function: extracting enough information from a hard-to-interpret signal to act optimally can itself be computationally hard. We also characterize tractability across approximation notions and identify their sources of difficulty. Under the probably approximately correct criterion, sample-based Bayesian learning is tractable if and only if the signal support is bounded. Our results provide justifications for bounded rationality, costly Bayesian inference, and sample-based Bayesian learning.
A coherence-gated Bayesian decision rule within Viscous Time Theory (VTT) frame is formed that proves boundedness and well-posedness, exact recovery of the Bayesian posterior at the neutral gate, an explicit perturbation bound, an odds decomposition, an exact Bayesian representation through an auxiliary admissibility e...
Raoul Bianchetti, Payam Danesh· Journal of Electrical Electr...· 0 citations
Simulations against group-sequential and always-valid frequentist baselines show that flat-prior posterior stopping exactly reproduces naive peeking, that a well-calibrated empirical Bayes prior achieves the lowest estimation error, and that expected-loss stopping minimizes regret only when shipping a null-effect varia...
Bayesian inference provides a unifying formalism for describing the inferences humans and other animals perform about features of the environment that change on fast timescales (moment-by-moment or trial-by-trial), as well as their learning of environmental contingencies and regularities that vary over slower time scal...
T. Kovács, Máté Lengyel· Current Opinion in Neurobiol...· 1 citation
We present a detailed comparison of Bayesian criteria with three non-informative priors - flat, Jeffreys, and scale-invariant - for testing a signal against an unknown background and compare them with the classical frequentist Li-Ma approach in the On/Off problem. We perform Monte Carlo simulations for various backgrou...
The most common dynamic borrowing approaches for external data, including how to incorporate multiple historical data sets, are reviewed and used in practice, using publicly available software, to perform important statistical tasks such as model selection, average treatment effect estimation and prior sensitivity anal...
Xin-Xin Chen, E. Braga, Joseph G. Ibrahim et al.· 0 citations
We represent a non-Bayesian agent as one who does not completely trust the information they receive. The behavioral expression of complete trust lies in a homogeneity property of Bayesian updating: posterior beliefs do not change if a signal is made arbitrarily rare by scaling down its likelihood vector. We show that s...
Jawwad Noor, Yu-Zhao Yang· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
