Statistical Inference and String Theory
arXiv:1305.3621
Abstract
In this note we expose some surprising connections between string theory and statistical inference. We consider a large collective of agents sweeping out a family of nearby statistical models for an M-dimensional manifold of statistical fitting parameters. When the agents making nearby inferences align along a d-dimensional grid, we find that the pooled probability that the collective reaches a correct inference is the partition function of a non-linear sigma model in d dimensions. Stability under perturbations to the original inference scheme requires the agents of the collective to distribute along two dimensions. Conformal invariance of the sigma model corresponds to the condition of a stable inference scheme, directly leading to the Einstein field equations for classical gravity. By summing over all possible arrangements of the agents in the collective, we reach a string theory. We also use this perspective to quantify how much an observer can hope to learn about the internal geometry of a superstring compactification. Finally, we present some brief speculative remarks on applications to the AdS/CFT correspondence and Lorentzian signature spacetimes.
arXiv commentv2: 31 pages, 1 figure, clarifications and references added, typos corrected
References in corpus (12)
- On the Origin of Gravity and the Laws of Newton
- Non-perturbative Effects in AdS5 * S5 String Theory and d=4 SUSY Yang-Mills
- Instantons in supersymmetric Yang-Mills and D-instantons in IIB superstring theory
- Multi-Instanton Calculus and the AdS/CFT Correspondence in N=4 Superconformal Field Theory
- Field Theories for Learning Probability Distributions
- Numerical Calabi-Yau metrics
- Some numerical results in complex differential geometry
- A Geometric Formulation of Occam's Razor for Inference of Parametric Distributions
- Evidence for F(uzz) Theory
- Instantons, Twistors, and Emergent Gravity
- Instantons, the Information Metric, and the AdS/CFT Correspondence
- Super Yang-Mills Theory as a Twistor Matrix Model