Assessing, Testing and Estimating the Amount of Fine-Tuning by Means of Active Information

• Published in: Entropy (Basel, Switzerland) Switzerland), 2022-09, Vol.24 (10), p.1323
• Main Authors: Díaz-Pachón, Daniel Andrés, Hössjer, Ola
• Format: Article
• Language: English
• Subjects: active information; Algorithms; Cosmology; Entropy; Evolutionary algorithms; exponential tilting; fine-tuning; functional information; Genetic algorithms; Hypotheses; Hypothesis testing; Internet/Web search services; Knowledge; large deviations; Learning; Markov chains; Mathematical research; Metropolis-Hastings; Moran model; Parameters; Search algorithms; statistical estimation and testing
• ISSN: 1099-4300; 1099-4300
• DOI: 10.3390/e24101323

A general framework is introduced to estimate how much external information has been infused into a search algorithm, the so-called active information. This is rephrased as a test of fine-tuning, where tuning corresponds to the amount of pre-specified knowledge that the algorithm makes use of in order to reach a certain target. A function quantifies specificity for each possible outcome of a search, so that the target of the algorithm is a set of highly specified states, whereas fine-tuning occurs if it is much more likely for the algorithm to reach the target as intended than by chance. The distribution of a random outcome of the algorithm involves a parameter θ that quantifies how much background information has been infused. A simple choice of this parameter is to use θf in order to exponentially tilt the distribution of the outcome of the search algorithm under the null distribution of no tuning, so that an exponential family of distributions is obtained. Such algorithms are obtained by iterating a Metropolis-Hastings type of Markov chain, which makes it possible to compute their active information under the equilibrium and non-equilibrium of the Markov chain, with or without stopping when the targeted set of fine-tuned states has been reached. Other choices of tuning parameters θ are discussed as well. Nonparametric and parametric estimators of active information and tests of fine-tuning are developed when repeated and independent outcomes of the algorithm are available. The theory is illustrated with examples from cosmology, student learning, reinforcement learning, a Moran type model of population genetics, and evolutionary programming.