Published on Sun May 02 2021

High Dimensional Decision Making, Upper and Lower Bounds

Farzad Pourbabaee
0
0
0
Abstract

A decision maker's utility depends on her action $a\in A \subset \mathbb{R}^d$ and the payoff relevant state of the world . One can define the value of acquiring new information as the difference between the maximum expected utility pre- and post information acquisition. In this paper, I find asymptotic results on the expected value of information as $d \to \infty$, by using tools from the theory of (sub)-Guassian processes and generic chaining.

Mon Apr 08 2019
Artificial Intelligence
Bounded rational decision-making from elementary computations that reduce uncertainty
In its most basic form, decision-making can be viewed as a computational process that progressively eliminates alternatives. Such processes are generally costly, meaning that the amount of uncertainty that can be reduced is limited. Here, we introduce the notion of elementary computation based on a fundamental principle
0
0
0
Wed Apr 01 2015
Machine Learning
Signatures of Infinity: Nonergodicity and Resource Scaling in Prediction, Complexity, and Learning
We introduce a simple analysis of the structural complexity ofinite-memory processes. Such processes are familiar from the well-known multi-arm Bandit problem. We contrast our analysis with computation-theoretic and statistical inference approaches.
0
0
0
Thu Nov 20 2003
Artificial Intelligence
Great Expectations. Part II: Generalized Expected Utility as a Universal Decision Rule
0
0
0
Mon Apr 15 2019
Machine Learning
Introduction to Multi-Armed Bandits
Multi-armed bandits a simple but very powerful framework for algorithms that make decisions over time under uncertainty. An enormous body of work has accumulated over the years, covered in several books and surveys. This book provides a more introductory, textbook-like treatment of the subject.
1
0
1
Mon Jan 18 2016
Machine Learning
Statistical Mechanics of High-Dimensional Inference
High-dimensional inference is a problem in the statistical physics of quenched disorder. Our analysis uncovers fundamental limits on the accuracy of inference in high dimensions. We also reveal that widely cherished inference algorithms like maximum likelihood (ML) and maximum-a posteriori (MAP) cannot achieve these limits.
0
0
0
Wed Feb 06 2013
Artificial Intelligence
Conditional Utility, Utility Independence, and Utility Networks
We introduce a new interpretation of two related notions - conditional utility and utility independence. Unlike the traditional interpretation, the new interpretation renders the notions the direct analogues of theirprobabilistic counterparts. We present the notion of utility networks, which do for utilities what Bayesian networks do for probabilities.
0
0
0