Complexity-calibrated benchmarks for machine learning reveal when prediction algorithms succeed and mislead.

Recurrent neural networks are used to forecast time series in finance, climate, language, and from many other domains. Reservoir computers are a particularly easily trainable form of recurrent neural network. Recently, a "next-generation" reservoir computer was introduced in which the memory trace involves only a finite number of previous symbols.

Initial-state dependence of thermodynamic dissipation for any quantum process.

Exact results about the nonequilibrium thermodynamics of open quantum systems at arbitrary timescales are obtained by considering all possible variations of initial conditions of a system. First we obtain a quantum-information theoretic equality for entropy production, valid for an arbitrary initial joint state of system and environment. For any finite-time process with a fixed initial environment, we then show that the system's loss of distinction-relative to the minimally dissipative state-exactly quantifies its thermodynamic dissipation.

Spectral simplicity of apparent complexity. II. Exact complexities and complexity spectra.

The meromorphic functional calculus developed in Part I overcomes the nondiagonalizability of linear operators that arises often in the temporal evolution of complex systems and is generic to the metadynamics of predicting their behavior. Using the resulting spectral decomposition, we derive closed-form expressions for correlation functions, finite-length Shannon entropy-rate approximates, asymptotic entropy rate, excess entropy, transient information, transient and asymptotic state uncertainties, and synchronization information of stochastic processes generated by finite-state hidden Markov models. This introduces analytical tractability to investigating information processing in discrete-event stochastic processes, symbolic dynamics, and chaotic dynamical systems.

Spectral simplicity of apparent complexity. I. The nondiagonalizable metadynamics of prediction.

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.

Transient Dissipation and Structural Costs of Physical Information Transduction.

A central result that arose in applying information theory to the stochastic thermodynamics of nonlinear dynamical systems is the information-processing second law (IPSL): the physical entropy of the Universe can decrease if compensated by the Shannon-Kolmogorov-Sinai entropy change of appropriate information-carrying degrees of freedom. In particular, the asymptotic-rate IPSL precisely delineates the thermodynamic functioning of autonomous Maxwellian demons and information engines. How do these systems begin to function as engines, Landauer erasers, and error correctors? We identify a minimal, and thus inescapable, transient dissipation of physical information processing, which is not captured by asymptotic rates, but is critical to adaptive thermodynamic processes such as those found in biological systems.