Evolutionary Data Theory: On the Similarities between Data Problems and Evolutionary Games

• URL: http://arxiv.org/abs/2605.26685v1
• Date: Tue, 26 May 2026 08:24:51 GMT
• Title: Evolutionary Data Theory: On the Similarities between Data Problems and Evolutionary Games
• Abstract summary: It is shown that this evolutionary interpretation remains universally meaningful, by proving convergence to a unique rest point.<n>A basic example of multi-objective optimization is shown as well as a related distribution problem.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Applying the concepts and formalisms from Evolutionary Game Theory to the data regime, the fundamental paradigms of Evolutionary Data Theory are introduced. Interpreting data in matrix form as evolutionary entities, input data is mapped to genes and organisms. Steered by genetic fitness and two evolutionary strategies, Dominant-Balanced and Altruistic-Selfish, data records and features conduct an evolutionary game. It is shown that this evolutionary interpretation remains universally meaningful, by proving convergence to a unique rest point, where all data features persist in the population. A basic example of multi-objective optimization is shown as well as a related distribution problem.

Related papers

• Self-Evolving Memory for Generative Recommendation [100.15207958893029]
  Generative recommendation has emerged as a promising end-to-end paradigm for personalized recommendation.<n>Existing evolving strategies, such as continual retraining and distillation-based adaptation, directly update the shared model parameters.<n>We propose a self-evolving memory paradigm for generative recommendation, aiming to enable effective evolution across heterogeneous behavioral patterns.
  arXiv  Detail & Related papers  (2026-09-14T14:00:38Z)
• Causal Modeling of Selection in Evolution [15.226308484865825]
  We argue that "selection" in common narratives takes two forms, which we term static and evolutionary selection, respectively.<n>Existing methods largely conflate these two forms and rely on an identical graphical model of selection.<n>We show that this model is valid for static settings but fails to characterize data under evolution, yielding false discovery results.<n>We introduce a new model that specifically characterizes evolutionary selection, and develop a sound and complete procedure for identifying such models from data across one or multiple environments or generations.
  arXiv  Detail & Related papers  (2026-06-04T04:16:06Z)
• Genetic AI: Evolutionary Games for ab initio dynamic Multi-Objective Optimization [0.0]
  Genetic AI is a novel method for multi-objective optimization without external parameters or predefined weights.<n>We present four evolutionary strategies: Dominant, Altruistic, Balanced and Selfish.<n>We show the universality of the approach on two decision problems.
  arXiv  Detail & Related papers  (2025-01-31T13:17:09Z)
• Range, not Independence, Drives Modularity in Biologically Inspired Representations [52.48094670415497]
  We develop a theory of when biologically inspired networks modularise their representation of source variables (sources)<n>We derive necessary and sufficient conditions on a sample of sources that determine whether the neurons in an optimal linear autoencoder modularise.<n>Our theory applies to any dataset, extending far beyond the case of statistical independence studied in previous work.
  arXiv  Detail & Related papers  (2024-10-08T17:41:37Z)
• Learning Divergence Fields for Shift-Robust Graph Representations [73.11818515795761]
  In this work, we propose a geometric diffusion model with learnable divergence fields for the challenging problem with interdependent data. We derive a new learning objective through causal inference, which can guide the model to learn generalizable patterns of interdependence that are insensitive across domains.
  arXiv  Detail & Related papers  (2024-06-07T14:29:21Z)
• Learning Discrete Concepts in Latent Hierarchical Models [73.01229236386148]
  Learning concepts from natural high-dimensional data holds potential in building human-aligned and interpretable machine learning models.<n>We formalize concepts as discrete latent causal variables that are related via a hierarchical causal model.<n>We substantiate our theoretical claims with synthetic data experiments.
  arXiv  Detail & Related papers  (2024-06-01T18:01:03Z)
• Note: Evolutionary Game Theory Focus Informational Health: The Cocktail Party Effect Through Werewolfgame under Incomplete Information and ESS Search Method Using Expected Gains of Repeated Dilemmas [0.0]
  We explore the state of information disruption caused by the cocktail party effect within the framework of non-perfect information games. We mathematically model and analyze the effects on the gain of each strategy choice and the formation process of evolutionary stable strategies (ESS) under the assumption that the pollution risk of fake news is randomly assigned.
  arXiv  Detail & Related papers  (2024-02-27T14:10:34Z)
• Evolutionary game theory: the mathematics of evolution and collective behaviours [1.4685355149711299]
  It summarises some of my recent research directions using evolutionary game theory methods. It includes the analysis of statistical properties of the number of (stable) equilibria in a random evolutionary game. It also includes the modelling of safety behaviours' evolution and the risk posed by advanced Artificial Intelligence technologies in a technology development race.
  arXiv  Detail & Related papers  (2023-11-24T13:42:55Z)
• DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion [66.21290235237808]
  We introduce an energy constrained diffusion model which encodes a batch of instances from a dataset into evolutionary states. We provide rigorous theory that implies closed-form optimal estimates for the pairwise diffusion strength among arbitrary instance pairs. Experiments highlight the wide applicability of our model as a general-purpose encoder backbone with superior performance in various tasks.
  arXiv  Detail & Related papers  (2023-01-23T15:18:54Z)
• Handling Distribution Shifts on Graphs: An Invariance Perspective [78.31180235269035]
  We formulate the OOD problem on graphs and develop a new invariant learning approach, Explore-to-Extrapolate Risk Minimization (EERM) EERM resorts to multiple context explorers that are adversarially trained to maximize the variance of risks from multiple virtual environments. We prove the validity of our method by theoretically showing its guarantee of a valid OOD solution.
  arXiv  Detail & Related papers  (2022-02-05T02:31:01Z)
• Towards a Theory of Evolution as Multilevel Learning [0.0]
  We apply the theory of learning to physically renormalizable systems in an attempt to develop a theory of biological evolution, including the origin of life, as multilevel learning. We formulate seven fundamental principles of evolution that appear to be necessary and sufficient to render a universe observable. We show that these principles entail the major features of biological evolution, including replication and natural selection.
  arXiv  Detail & Related papers  (2021-10-27T17:21:16Z)
• A General Theory for the Evolution of Application Models -- Full version [0.0]
  This theory makes a distinction between the underlying information structure at the conceptual level, its evolution on the one hand, and the description and semantics of operations on the information structure and its population on the other hand. Main issues within this theory are object typing, type relatedness and identification of objects. In this general theory, the underlying data model is a parameter, making the theory applicable for a wide range of modelling techniques.
  arXiv  Detail & Related papers  (2021-05-18T17:24:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.