One and Done? Optimal Decisions From Very Few Samples

Cognitive Science 38 (4):599-637 (2014)

Abstract
In many learning or inference tasks human behavior approximates that of a Bayesian ideal observer, suggesting that, at some level, cognition can be described as Bayesian inference. However, a number of findings have highlighted an intriguing mismatch between human behavior and standard assumptions about optimality: People often appear to make decisions based on just one or a few samples from the appropriate posterior probability distribution, rather than using the full distribution. Although sampling-based approximations are a common way to implement Bayesian inference, the very limited numbers of samples often used by humans seem insufficient to approximate the required probability distributions very accurately. Here, we consider this discrepancy in the broader framework of statistical decision theory, and ask: If people are making decisions based on samples—but as samples are costly—how many samples should people use to optimize their total expected or worst-case reward over a large number of decisions? We find that under reasonable assumptions about the time costs of sampling, making many quick but locally suboptimal decisions based on very few samples may be the globally optimal strategy over long periods. These results help to reconcile a large body of work showing sampling-based or probability matching behavior with the hypothesis that human cognition can be understood in Bayesian terms, and they suggest promising future directions for studies of resource-constrained cognition
Keywords Sampling  Bounded rationality  Bayesian  Computational  Inference
Categories (categorize this paper)
DOI 10.1111/cogs.12101
Options
Edit this record
Mark as duplicate
Export citation
Find it on Scholar
Request removal from index
Revision history

Download options

Our Archive


Upload a copy of this paper     Check publisher's policy     Papers currently archived: 41,668
Through your library

References found in this work BETA

Vison.David Marr - 1982 - W. H. Freeman.

View all 27 references / Add more references

Citations of this work BETA

Subjective Probability as Sampling Propensity.Thomas Icard - 2016 - Review of Philosophy and Psychology 7 (4):863-903.

View all 23 citations / Add more citations

Similar books and articles

When Can Non‐Commutative Statistical Inference Be Bayesian?Miklós Rédei - 1992 - International Studies in the Philosophy of Science 6 (2):129-132.
Experiential Limitation in Judgment and Decision.Ulrike Hahn - 2014 - Topics in Cognitive Science 6 (2):229-244.
Universal Bayesian Inference?David Dowe & Graham Oppy - 2001 - Behavioral and Brain Sciences 24 (4):662-663.

Analytics

Added to PP index
2014-01-28

Total views
36 ( #225,773 of 2,250,069 )

Recent downloads (6 months)
7 ( #246,958 of 2,250,069 )

How can I increase my downloads?

Downloads

My notes

Sign in to use this feature