Spectral simplicity of apparent complexity. I: The nondiagonalizable metadynamics of prediction
From MaRDI portal
Publication:4565944
Prediction theory (aspects of stochastic processes) (60G25) Statistical aspects of information-theoretic topics (62B10) Markov processes: estimation; hidden Markov models (62M05) Inference from stochastic processes and spectral analysis (62M15) Inference from stochastic processes and prediction (62M20) Applications of statistics to physics (62P35)
Abstract: Virtually all questions that one can ask about the behavioral and structural complexity of a stochastic process reduce to a linear algebraic framing of a time evolution governed by an appropriate hidden-Markov process generator. Each type of question---correlation, predictability, predictive cost, observer synchronization, and the like---induces a distinct generator class. Answers are then functions of the class-appropriate transition dynamic. Unfortunately, these dynamics are generically nonnormal, nondiagonalizable, singular, and so on. Tractably analyzing these dynamics relies on adapting the recently introduced meromorphic functional calculus, which specifies the spectral decomposition of functions of nondiagonalizable linear operators, even when the function poles and zeros coincide with the operator's spectrum. Along the way, we establish special properties of the projection operators that demonstrate how they capture the organization of subprocesses within a complex system. Circumventing the spurious infinities of alternative calculi, this leads in the sequel, Part II, to the first closed-form expressions for complexity measures, couched either in terms of the Drazin inverse (negative-one power of a singular operator) or the eigenvalues and projection operators of the appropriate transition dynamic.
Recommendations
- Spectral simplicity of apparent complexity. II: Exact complexities and complexity spectra
- Process dimension of classical and non-commutative processes
- Exact complexity: the spectral decomposition of intrinsic computation
- Properties of the statistical complexity functional and partially deterministic HMMs
- Complexity of dynamics as variability of predictability
Cites work
- A Mathematical Theory of Communication
- Anatomy of a bit: information in a time series observation
- Approximations for the Entropy for Functions of Markov Chains
- Asymptotic synchronization for finite-state sources
- Computational mechanics: pattern and prediction, structure and simplicity.
- Elements of Information Theory
- Equivalence of state representations for hidden Markov models
- Evolutionary dynamics. Exploring the equations of life.
- Exact complexity: the spectral decomposition of intrinsic computation
- Exact synchronization for finite-state sources
- Exponential bounds for convergence of entropy rate approximations in hidden Markov models satisfying a path-mergeability condition
- Finitary Codings and Weak Bernoulli Partitions
- Generalized inverses. Theory and applications.
- Hidden Markov models for stochastic thermodynamics
- How hidden are hidden processes? A primer on crypticity and entropy convergence
- scientific article; zbMATH DE number 3140804 (Why is no real title available?)
- scientific article; zbMATH DE number 3145626 (Why is no real title available?)
- scientific article; zbMATH DE number 3664335 (Why is no real title available?)
- scientific article; zbMATH DE number 46484 (Why is no real title available?)
- scientific article; zbMATH DE number 215190 (Why is no real title available?)
- scientific article; zbMATH DE number 3228255 (Why is no real title available?)
- scientific article; zbMATH DE number 3307452 (Why is no real title available?)
- Information accessibility and cryptic processes
- Informational and causal architecture of continuous-time renewal processes
- Leveraging environmental correlations: the thermodynamics of requisite variety
- Mathematical population genetics. I: Theoretical introduction.
- Nonequilibrium statistical physics of small systems. Fluctuation relations and beyond
- Optimal causal inference: estimating stored information and approximating causal architecture
- Predictability, complexity, and learning
- Prediction, retrodiction, and the amount of information stored in the present
- Predictive rate-distortion for infinite-order Markov processes
- Probabilistic automata
- Quantum automata and quantum grammars
- Regularities unseen, randomness observed: Levels of entropy convergence
- Spectra of digraphs
- Spectral Theory. I Convergence to Projections
- Structure and randomness of continuous-time, discrete-event processes
- Synchronization and control in intrinsic and designed computation: An information-theoretic analysis of competing models of stochastic computation
- The calculi of emergence: Computation, dynamics and induction
- Toward a quantitative theory of self-generated complexity
Cited in
(3)
This page was built for publication: Spectral simplicity of apparent complexity. I: The nondiagonalizable metadynamics of prediction
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4565944)
