196 citations · 2.3k across the 104 of their papers we have counts for
8 papers · 1 filter
Stochastic gradient method with accelerated stochastic dynamics
Masayuki Ohzeki
In this paper, we propose a novel technique to implement stochastic gradient methods, which are beneficial for learning from large datasets, through accelerated stochastic dynamics…
Optimization of Markov process violates detailed balance condition
Kazutaka Takahashi, Masayuki Ohzeki
We consider the optimization of Markovian dynamics to pursue the fastest convergence to the stationary state. The brachistochrone method is applied to the continuous-time master eq…
L_1-regularized Boltzmann machine learning using majorizer minimization
Masayuki Ohzeki
We propose an inference method to estimate sparse interactions and biases according to Boltzmann machine learning. The basis of this method is regularization, which is often…
Mathematical understanding of detailed balance condition violation and its application to Langevin dynamics
M. Ohzeki, A. Ichiki
We develop an efficient sampling method by simulating Langevin dynamics with an artificial force rather than a natural force by using the gradient of the potential energy. The stan…
Full-order fluctuation-dissipation relation for a class of non-equilibrium steady states
Akihisa Ichiki, Masayuki Ohzeki
Acceleration of relaxation toward a fixed stationary distribution via violation of detailed balance was reported in the context of a Markov chain Monte Carlo method recently. Inspi…
Hysteretic transition of coarse-grained power grid model on small-world network
Eiichi Sasaki, Masayuki Ohzeki, Yoshito Ohta
We study synchronous phenomena of a coarse-grained power grid model, the swing equation, on small-world networks. We show that its steady state, which stands for the normal operati…