Santa Fe Institute

Seminar

March 14, 2013
12:15 PM
Collins Conference Room

Amos Golan (Department of Economics, American University)

Abstract.   Info-metrics is the science and art of quantitatively processing information and inference. It crosses the boundaries of all sciences and provides the universal mathematical and philosophical foundations for inference with finite, noisy or incomplete information. Info-metrics lies in the intersection of information theory, inference, mathematics, statistics, complexity, decision analysis and the philosophy of science. From mystery solving to the formulation of all theories – we must infer with limited and blurry observable information. The study of info-metrics helps in resolving a major challenge for all scientists and all decision makers of how to reason under conditions of incomplete information. Though optimal inference and efficient information processing are at the heart of info-metrics, these issues cannot be developed and studied without understanding information, entropy, statistical inference, probability theory, information and complexity theory as well as the meaning and value of information, data analysis and other related concepts from across the sciences.

In this talk I will discuss some of the issues related to information and information processing. I will concentrate on the basic problem of inference with finite information and with a minimal set of assumptions or structure. I will start by discussing the different types of available information. Then I will discuss some of the necessary requirements for constructing an efficient information processing rule. Building on the classical Maximum Entropy formalism (Jaynes, 1957), I will construct a generic and universal framework for inference with observable (and unobservable) information. I will show that the class of information-theoretic methods of inference is a sub-class of this generic framework. I will pay special attention to the interpretation of the different quantities and for showing the relationships between Information-Theoretic (IT) methods of estimation and traditional (including Bayesian) methods. Within the class of IT methods I will discuss the specific case of stochastic moments methods of inference and the advantages of this approach. I will also present a number of representative examples of applied and predicted games. I will conclude with a discussion of some open questions in information processing.

Purpose: Resident Faculty

SFI Host: Jennifer Dunne

More Info

• * SFI community lectures are free, open, & accessible to the public.
• * Seminars & colloquia are geared for scientists but free & open to the interested public.
• * All other SFI events are by invitation only.
• * Note: We are unable to accommodate members of the public for SFI's limited lunch service; you're welcome to bring your own.