5 papers
Self-Regulating Annealing in Heavy-Tailed Diffusion Models
Keito Wakatsuki, Hideaki Shimazaki
Diffusion models have emerged as a leading framework for deep generative modeling. While the standard Gaussian formulation is theoretically convenient, its suitability for heavy-ta…
Enhancing diffusion models with Gaussianization preprocessing
Li Cunzhi, Louis Kang, Hideaki Shimazaki
Diffusion models are a class of generative models that have demonstrated remarkable success in tasks such as image generation. However, one of the bottlenecks of these models is sl…
State-space kinetic Ising model reveals task-dependent entropy flow in sparsely active nonequilibrium neuronal dynamics
Ken Ishihara, Hideaki Shimazaki
Neuronal ensemble activity, including coordinated and oscillatory patterns, exhibits hallmarks of nonequilibrium systems with time-asymmetric trajectories to maintain their organiz…
Explosive neural networks via higher-order interactions in curved statistical manifolds
Miguel Aguilera, Pablo A. Morales, Fernando E. Rosas +1
Higher-order interactions underlie complex phenomena in systems such as biological and artificial neural networks, but their study is challenging due to the scarcity of tractable m…
A projected nonlinear state-space model for forecasting time series signals
Christian Donner, Anuj Mishra, Hideaki Shimazaki
Learning and forecasting stochastic time series is essential in various scientific fields. However, despite the proposals of nonlinear filters and deep-learning methods, it remains…