Stochastic Process Turing Machines
David Wolpert, Jordan Scharnhorst

TL;DR
This paper introduces stochastic process Turing machines and a new complexity measure called stochastic depth, enabling the analysis of complex stochastic systems within a formal computational framework, bridging gaps in existing measures.
Contribution
It defines stochastic process Turing machines and stochastic depth, extending complexity measures to stochastic systems and connecting them with thermodynamic properties.
Findings
Stochastic depth relates to Kolmogorov and Levin complexities.
Stochastic process Turing machines model complex stochastic systems.
New complexity measures capture properties of real-world stochastic processes.
Abstract
Computer science theory provides many different measures of complexity of a system including Kolmogorov complexity, logical depth, computational depth, and Levin complexity. However, these measures are all defined only for deterministic Turing machines, i.e., deterministic dynamics of the underlying generative process whose output we are interested in. Therefore, by construction they cannot capture complexity of the output of stochastic processes - like those in the real world. Motivated by this observation, we combine probabilistic Turing machines with a prior over the inputs to the Turing machine to define a complete stochastic process of Turing machines. We call this a stochastic process Turing machine. We use stochastic process Turing machines to define a set of new generative complexity measures based on Turing machines, which we call stochastic depth. As we discuss, stochastic…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSmart Grid Security and Resilience · Data Stream Mining Techniques · Machine Learning and Algorithms
