Learning in adaptive systems

On staring into scopophilic abysses

October 19, 2019 — January 22, 2020

hidden variables
hierarchical models
machine learning


Heuristic about the what science can tell us about systems that we learn and that learn us back.

What the success of machine learning tells us about the structure of the world. Non-arbitrage versus hypothesis tests. Adversarial versus random noise. Economic systems. The bit before attaining equilibrium. Homogenaeity versus local regularities. Our tendency to look for universals.

1 Incoming

Scale effects in economics are a subject of the 2019 Nobel Memorial economics prize. Internal versus external validity in economics. Daniel Lakens reviews (Yarkoni 2019) on generalisability in psychology.

2 Stylised comparison

Static world Adaptive world
People are… the objects the subjects
Individual behaviour emerges from… fixed personalities that we can discover networks and group dynamics
Society is… a system with static rules a game with rules made up by players as they go along
We should… learn the truth and act upon it guess a better next move than the other actors
Learning means… accepting a hypothesis based on P-value betting on the best portfolio of actions

3 As pertains to AI

Embedded agency and other framings of the Machine Intelligence Research Institute taxonomise some related ideas from the perspective of building intelligences that interact with the world which seem to interact with these.

4 References

Bieniawski, and Wolpert. 2004. Adaptive, Distributed Control of Constrained Multi-Agent Systems.” In Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems-Volume 3.
Birhane, and Sumpter. 2022. The Games We Play: Critical Complexity Improves Machine Learning.”
Deschâtres, and Sornette. 2005. Dynamics of Book Sales: Endogenous Versus Exogenous Shocks in Complex Networks.” Physical Review E.
Galesic, Barkoczi, Berdahl, et al. 2022. Beyond Collective Intelligence: Collective Adaptation.”
Kauffman, and Johnsen. 1991. Coevolution to the Edge of Chaos: Coupled Fitness Landscapes, Poised States, and Coevolutionary Avalanches*.” Journal of Theoretical Biology.
Lansing. 2003. Complex Adaptive Systems.” Annual Review of Anthropology.
Leibon, Pauls, Rockmore, et al. 2010. “Statistical Learning for Complex Systems an Example-Driven Introduction.”
Lux. 1995. Herd Behaviour, Bubbles and Crashes.” The Economic Journal.
Lux, and Sornette. 2002. On Rational Bubbles and Fat Tails.” Journal of Money, Credit and Banking.
Newell, and Wasson. 2002. “Social System Vs Solar System: Why Policy Makers Need History.” In.
Simon. 1962. “The Architecture of Complexity.” Proceedings of the American Philosophical Society.
———. 1996. The Sciences of the Artificial.
Sornette. 2003. Critical Market Crashes.” Physics Reports.
———. 2006. Endogenous Versus Exogenous Origins of Crises.” In Extreme Events in Nature and Society. The Frontiers Collection.
———. 2009a. Probability Distributions in Complex Systems.” In Encyclopedia of Complexity and Systems Science.
———. 2009b. Dragon-Kings, Black Swans and the Prediction of Crises.” arXiv:0907.4290 [Physics].
Sornette, and Cauwels. 2012. The Illusion of the Perpetual Money Machine.” SSRN Scholarly Paper ID 2191509. Notenstein Academy White Paper Series.
———. 2015. Managing Risk in a Creepy World.” Journal of Risk Management in Financial Institutions.
Understanding Development and Poverty Alleviation.” 2019.
Vincent. 2006. “Carcinogenesis As an Evolutionary Game.” Advances in Complex Systems.
Walker, and Janssen. 2002. Rangelands, Pastoralists and Governments: Interlinked Systems of People and Nature.” Philosophical Transactions of the Royal Society B: Biological Sciences.
Watson, Buckley, and Mills. 2011. Optimization in ‘Self-Modeling’ Complex Adaptive Systems.” Complexity.
Yarkoni. 2019. The Generalizability Crisis.” Preprint.
Yukalov, Yukalova, and Sornette. 2009. Punctuated Evolution Due to Delayed Carrying Capacity.” Physica D: Nonlinear Phenomena.