5 papers
Non-Equilibrium Model Selection via Finite-Time Thermodynamics
Masayuki Ohzeki
Information criteria such as WAIC and WBIC extend model selection to singular learning machines, but they are usually derived for equilibrium posteriors. We formulate a finite-time…
Daydreaming algorithm for Biased Patterns
Mikiya Doi, Masayuki Ohzeki, Federico Ricci-Tersenghi
The \emph{Daydreaming} algorithm has been recently proposed in Ref.~\cite{Serricchio2025} as a learning rule that simultaneously reinforces stored patterns and suppresses spurious…
Nonreversible Gauge Fields in Fokker--Planck Dynamics: Supersymmetric Hamiltonians and Learned Finite Forces
Masayuki Ohzeki
We formulate stationary-density-preserving nonreversible perturbations of Fokker--Planck dynamics as gauge fields that deform relaxation spectra while leaving the invariant state f…
Fourier Analysis of Parameterized Quantum Circuits and the Barren Plateau Problem
Shun Okumura, Masayuki Ohzeki
We show the relationship between the Fourier coefficients and the barren plateau problem emerging in parameterized quantum circuits. In particular, the sum of squares of the Fourie…
Application of time-series quantum generative model to financial data
Shun Okumura, Masayuki Ohzeki, Masaya Abe
Despite proposing a quantum generative model for time series that successfully learns correlated series with multiple Brownian motions, the model has not been adapted and evaluated…