English
Related papers

Related papers: Blackwell-Monotone Updating Rules

200 papers

We consider an agent who represents uncertainty about the environment via a possibly misspecified model. Each period, the agent takes an action, observes a consequence, and uses Bayes' rule to update her belief about the environment. This…

Theoretical Economics · Economics 2019-10-24 Ignacio Esponda , Demian Pouzo , Yuichi Yamamoto

It has been shown that one can accommodate data (Bayes) and constraints (MaxEnt) in one method, the method of Maximum (relative) Entropy (ME) (Giffin 2007). In this paper we show a complex agent based example of inference with two different…

Methodology · Statistics 2016-09-08 Adom Giffin

Bayesian analyses are often performed using so-called noninformative priors, with a view to achieving objective inference about unknown parameters on which available data depends. Noninformative priors depend on the relationship of the data…

Methodology · Statistics 2013-08-14 Nicholas Lewis

Boolean networks are discrete dynamical systems where each automaton has its own Boolean function for computing its state according to the configuration of the network. The updating mode then determines how the configuration of the network…

Dynamical Systems · Mathematics 2021-06-30 Loïc Paulevé , Sylvain Sené

Much is now known about the consistency of Bayesian updating on infinite-dimensional parameter spaces with independent or Markovian data. Necessary conditions for consistency include the prior putting enough weight on the correct…

Statistics Theory · Mathematics 2022-03-18 Cosma Rohilla Shalizi

We develop a result on expected posteriors for Bayesians with heterogenous priors, dubbed information validates the prior (IVP). Under familiar ordering requirements, Anne expects a (Blackwell) more informative experiment to bring Bob's…

Theoretical Economics · Economics 2022-12-29 Navin Kartik , Frances Lee , Wing Suen

Natural revision seems so natural: it changes beliefs as little as possible to incorporate new information. Yet, some counterexamples show it wrong. It is so conservative that it never fully believes. It only believes in the current…

Artificial Intelligence · Computer Science 2025-05-27 Paolo Liberatore

Loss-based updating, including generalized Bayes, Gibbs, and quasi-posteriors, replaces likelihoods by a user-chosen loss and produces a posterior-like distribution via exponential tilt. We give a decision-theoretic characterization that…

Methodology · Statistics 2026-02-03 Kenichiro McAlinn , Kōsaku Takanashi

I propose a normative updating rule, extended Bayesianism, for the incorporation of probabilistic information arising from the process of becoming more aware. Extended Bayesianism generalizes standard Bayesian updating to allow the…

Theoretical Economics · Economics 2021-10-06 Evan Piermont

We study learning dynamics induced by strategic agents who repeatedly play a game with an unknown payoff-relevant parameter. In this dynamics, a belief estimate of the parameter is repeatedly updated given players' strategies and realized…

Computer Science and Game Theory · Computer Science 2021-09-06 Manxi Wu , Saurabh Amin , Asuman Ozdaglar

This paper provides a behavioral analysis of conservatism in beliefs. I introduce a new axiom, Dynamic Conservatism, that relaxes Dynamic Consistency when information and prior beliefs "conflict." When the agent is a subjective expected…

Theoretical Economics · Economics 2021-02-02 Matthew Kovach

We introduce a general methodology of update rules accounting for arbitrary interevent time distributions in simulations of interacting agents. In particular we consider update rules that depend on the state of the agent, so that the update…

Physics and Society · Physics 2011-07-19 Juan Fernández-Gracia , V. M. Eguíluz , M. San Miguel

Despite the tremendous empirical success of quantum theory there is still widespread disagreement about what it can tell us about the nature of the world. A central question is whether the theory is about our knowledge of reality, or a…

Quantum Physics · Physics 2019-06-10 Sally Shrapnel , Fabio Costa , Gerard Milburn

We present an analytical policy update rule that is independent of parametric function approximators. The policy update rule is suitable for optimizing general stochastic policies and has a monotonic improvement guarantee. It is derived…

Artificial Intelligence · Computer Science 2022-07-18 Hepeng Li , Nicholas Clavette , Haibo He

Methods for probability updating, of which Bayesian conditionalization is the most well-known and widely used, are modeling tools that aim to represent the process of modifying an initial epistemic state, typically represented by a prior…

Logic in Computer Science · Computer Science 2025-12-01 Tommaso Flaminio , Lluis Godo , Gluliano Rosella

Currently, there is renewed interest in the problem, raised by Shafer in 1985, of updating probabilities when observations are incomplete (or set-valued). This is a fundamental problem, and of particular interest for Bayesian networks.…

Artificial Intelligence · Computer Science 2014-08-08 Gert de Cooman , Marco Zaffalon

What is information? Is it physical? We argue that in a Bayesian theory the notion of information must be defined in terms of its effects on the beliefs of rational agents. Information is whatever constrains rational beliefs and therefore…

Data Analysis, Statistics and Probability · Physics 2016-09-08 Ariel Caticha

We study learning dynamics induced by strategic agents who repeatedly play a game with an unknown payoff-relevant parameter. In each step, an information system estimates a belief distribution of the parameter based on the players'…

Systems and Control · Electrical Eng. & Systems 2020-10-20 Manxi Wu , Saurabh Amin , Asuman Ozdaglar

This paper discusses how a measure of uncertainty representing a state of knowledge can be updated when a new information, which may be pervaded with uncertainty, becomes available. This problem is considered in various framework, namely:…

Artificial Intelligence · Computer Science 2013-04-05 Didier Dubois , Henri Prade

Bayesian optimization is a coherent, ubiquitous approach to decision-making under uncertainty, with applications including multi-arm bandits, active learning, and black-box optimization. Bayesian optimization selects decisions (i.e.…

Machine Learning · Computer Science 2023-12-13 Samuel Stanton , Wesley Maddox , Andrew Gordon Wilson