Tatsuaki Wada
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Tatsuaki Wada has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Antonio Maria Scarfone
Istituto dei Sistemi Complessi del Consiglio Nazionale delle Ricerche (ISC-CNR) c/o Politecnico di Torino
13 shared publications - Hiroshi Matsuzoe
Department of Computer Science Nagoya Institute of Technology 466-8555 Nagoya Japan
3 shared publications Antonio M. Scarfone
Istituto dei Sistemi Complessi, Consiglio Nazionale delle Ricerche, (ISC-CNR) c/o Politecnico di Torino, Corso Duca degli Abruzzi 24, Torino 10129, Italy
2 shared publicationsHiroshi Matsuzoe
Department of Computer Science, Nagoya Institute of Technology, Gokiso-cho, Showa-ku, Nagoya, Aichi 466-8555, Japan
2 shared publications- Sumanto Chanda
Indian Institute of Astrophysics Block 2 100 Feet Road 560034 Koramangala Bengaluru Karnataka India
2 shared publications - Velimir M. Ilic
Mathematical Institute of the Serbian Academy of Sciences and Arts, Kneza Mihaila 36, 11000 Beograd, Serbia
2 shared publications
Latest Publications
- 8 October 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Geometric Methods in Modern Physics
Reframing of information geometry via symmetric teleparallel gravity
Information geometry has traditionally been formulated within the framework of Riemannian geometry and dual affine connections. This work aims to reframe the foundational structure of information geometry by introducing the geometric machinery of symmetric teleparallel gravity. By requiring both curvature and torsion to vanish globally on the statistical manifold, it is demonstrated that the fundamental properties of the information space can be entirely encoded in the non-metricity tensor. This approach clarifies the distinction between the general [Formula: see text]-parameterized case and the [Formula: see text]- or [Formula: see text]-parameterized cases, which correspond to general symmetric teleparallel gravity and its coincident gauge, respectively. Specifically, the [Formula: see text]- or [Formula: see text]-coordinates emerge as special coordinates in the coincident gauge, where the connection coefficients vanish.
- 8 October 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Geometric Methods in Modern Physics
Reframing of information geometry via symmetric teleparallel gravity
Information geometry has traditionally been formulated within the framework of Riemannian geometry and dual affine connections. This work aims to reframe the foundational structure of information geometry by introducing the geometric machinery of symmetric teleparallel gravity. By requiring both curvature and torsion to vanish globally on the statistical manifold, it is demonstrated that the fundamental properties of the information space can be entirely encoded in the non-metricity tensor. This approach clarifies the distinction between the general [Formula: see text]-parameterized case and the [Formula: see text]- or [Formula: see text]-parameterized cases, which correspond to general symmetric teleparallel gravity and its coincident gauge, respectively. Specifically, the [Formula: see text]- or [Formula: see text]-coordinates emerge as special coordinates in the coincident gauge, where the connection coefficients vanish.
- Open Access
Reconsideration of Information-Theoretic Principles—Perspective from the Dual Probability Distribution
We reconsider information-theoretic principles, such as the maximum entropy principle/minimum Massieu potential principle, from the perspective of the dual probability distribution. This is introduced through Sanov’s Lemma for the multinomial distribution. The dual correspondence becomes asymptotically manifest. The Massieu potential is rewritten as the Kullback–Leibler divergence between the dual probability distribution and the dual reference distribution. Similarly, the dual potential is rewritten as the cumulant generating function with respect to the dual reference distribution. This perspective gives us new insight into information-theoretic principles. As the dual probability distribution naturally arises in data sampling, we anticipate that this new perspective will play a significant role in data analysis.
Open AccessReconsideration of Information-Theoretic Principles—Perspective from the Dual Probability Distribution
We reconsider information-theoretic principles, such as the maximum entropy principle/minimum Massieu potential principle, from the perspective of the dual probability distribution. This is introduced through Sanov’s Lemma for the multinomial distribution. The dual correspondence becomes asymptotically manifest. The Massieu potential is rewritten as the Kullback–Leibler divergence between the dual probability distribution and the dual reference distribution. Similarly, the dual potential is rewritten as the cumulant generating function with respect to the dual reference distribution. This perspective gives us new insight into information-theoretic principles. As the dual probability distribution naturally arises in data sampling, we anticipate that this new perspective will play a significant role in data analysis.
- Open Access
Non-Metricity in Information Geometry
The importance of non-metricity in information geometry is described through studies on gradient flow from the perspective of Weyl geometry. The Amari–Centsov tensor is the non-metricity tensor with respect to the connection and Fisher metric . We derive the explicit expression of the connection based on the non-metricity . The scalar field obtained from a potential function in information geometry plays a key role and characterizes Weyl’s gauge field, Weyl’s non-metricity, and the rate of the potential function during the associated gradient flow.Open AccessNon-Metricity in Information Geometry
The importance of non-metricity in information geometry is described through studies on gradient flow from the perspective of Weyl geometry. The Amari–Centsov tensor is the non-metricity tensor with respect to the connection and Fisher metric . We derive the explicit expression of the connection based on the non-metricity . The scalar field obtained from a potential function in information geometry plays a key role and characterizes Weyl’s gauge field, Weyl’s non-metricity, and the rate of the potential function during the associated gradient flow. - 15 September 2025
- Published by Physical Society of Japan in Journal of the Physical Society of Japan
- Vol. 94 (9)
Sliding Mode Control of an Electric Charge in a Non-linear Capacitor with Negative Differential Capacitance
- 15 September 2025
- Published by Physical Society of Japan in Journal of the Physical Society of Japan
- Vol. 94 (9)
Sliding Mode Control of an Electric Charge in a Non-linear Capacitor with Negative Differential Capacitance
- 26 August 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Geometric Methods in Modern Physics
- Vol. 23 (12)
Weyl symmetry of the gradient-flow in information geometry
In this paper, we have revisited the gradient-flow in information geometry from the perspective of Weyl symmetry. The gradient-flow equations are derived from the proposed action which is invariant under Weyl’s gauge transformations. In Weyl integrable geometry, we have related Amari’s [ ]-connections in information geometry to the Weyl invariant connection on the Riemannian manifold equipped with the scaled metric.
- 26 August 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Geometric Methods in Modern Physics
- Vol. 23 (12)
Weyl symmetry of the gradient-flow in information geometry
In this paper, we have revisited the gradient-flow in information geometry from the perspective of Weyl symmetry. The gradient-flow equations are derived from the proposed action which is invariant under Weyl’s gauge transformations. In Weyl integrable geometry, we have related Amari’s [ ]-connections in information geometry to the Weyl invariant connection on the Riemannian manifold equipped with the scaled metric.
- Open Access
Onsager’s Non-Equilibrium Thermodynamics as Gradient Flow in Information Geometry
We consider Onsager’s non-equilibrium thermodynamics from the perspective of the gradient flow in information geometry. Assuming Onsager’s reciprocal relations, we can regard his phenomenological equations as gradient-flow equations and develop two different gradient-flow models. We consider their features and their relations. Both models are applied to the ideal gas and van der Waals gas.
Open AccessOnsager’s Non-Equilibrium Thermodynamics as Gradient Flow in Information Geometry
We consider Onsager’s non-equilibrium thermodynamics from the perspective of the gradient flow in information geometry. Assuming Onsager’s reciprocal relations, we can regard his phenomenological equations as gradient-flow equations and develop two different gradient-flow models. We consider their features and their relations. Both models are applied to the ideal gas and van der Waals gas.
- 22 July 2024
- Published by Springer Nature in The European Physical Journal B
- Vol. 97 (7) , 1-12
A Hamiltonian approach to the gradient-flow equations in information geometry
- 22 July 2024
- Published by Springer Nature in The European Physical Journal B
- Vol. 97 (7) , 1-12
A Hamiltonian approach to the gradient-flow equations in information geometry
- Open Access
Multi-Additivity in Kaniadakis Entropy
It is known that Kaniadakis entropy, a generalization of the Shannon–Boltzmann–Gibbs entropic form, is always super-additive for any bipartite statistically independent distributions. In this paper, we show that when imposing a suitable constraint, there exist classes of maximal entropy distributions labeled by a positive real number that makes Kaniadakis entropy multi-additive, i.e., , under the composition of two statistically independent and identically distributed distributions , with reduced distributions and belonging to the same class.Open AccessMulti-Additivity in Kaniadakis Entropy
It is known that Kaniadakis entropy, a generalization of the Shannon–Boltzmann–Gibbs entropic form, is always super-additive for any bipartite statistically independent distributions. In this paper, we show that when imposing a suitable constraint, there exist classes of maximal entropy distributions labeled by a positive real number that makes Kaniadakis entropy multi-additive, i.e., , under the composition of two statistically independent and identically distributed distributions , with reduced distributions and belonging to the same class. - 29 December 2023
- Published by World Scientific Pub Co Pte Ltd in International Journal of Geometric Methods in Modern Physics
- Vol. 21 (05)
Mechanics of geodesics in information geometry and black hole thermodynamics
In this paper, we shall discuss the theory of geodesics in information geometry, and an application in astrophysics. We will study how gradient flows in information geometry describe geodesics, explore the related mechanics by introducing a constraint, and apply our theory to Gaussian model and black hole thermodynamics. Thus, we demonstrate how deformation of gradient flows leads to more general Randers–Finsler metrics, describe Hamiltonian mechanics that derive from a constraint, and prove duality via canonical transformation. We also verified our theories for a deformation of the Gaussian model, and described dynamical evolution of flat metrics for Kerr and Reissner–Nordström black holes.
- 29 December 2023
- Published by World Scientific Pub Co Pte Ltd in International Journal of Geometric Methods in Modern Physics
- Vol. 21 (05)
Mechanics of geodesics in information geometry and black hole thermodynamics
In this paper, we shall discuss the theory of geodesics in information geometry, and an application in astrophysics. We will study how gradient flows in information geometry describe geodesics, explore the related mechanics by introducing a constraint, and apply our theory to Gaussian model and black hole thermodynamics. Thus, we demonstrate how deformation of gradient flows leads to more general Randers–Finsler metrics, describe Hamiltonian mechanics that derive from a constraint, and prove duality via canonical transformation. We also verified our theories for a deformation of the Gaussian model, and described dynamical evolution of flat metrics for Kerr and Reissner–Nordström black holes.
- Open Access
Mechanics of geodesics in Information geometry and Black Hole Thermodynamics
In this article we shall discuss the theory of geodesics in information geometry, and an application in astrophysics. We will study how gradient flows in information geometry describe geodesics, explore the related mechanics by introducing a constraint, and apply our theory to Gaussian model and black hole thermodynamics. Thus, we demonstrate how deformation of gradient flows leads to more general Randers-Finsler metrics, describe Hamiltonian mechanics that derive from a constraint, and prove duality via canonical transformation. We also verified our theories for a deformation of the Gaussian model, and described dynamical evolution of flat metrics for Kerr and Reissner-Nordstr\"om black holes.
Open AccessMechanics of geodesics in Information geometry and Black Hole Thermodynamics
In this article we shall discuss the theory of geodesics in information geometry, and an application in astrophysics. We will study how gradient flows in information geometry describe geodesics, explore the related mechanics by introducing a constraint, and apply our theory to Gaussian model and black hole thermodynamics. Thus, we demonstrate how deformation of gradient flows leads to more general Randers-Finsler metrics, describe Hamiltonian mechanics that derive from a constraint, and prove duality via canonical transformation. We also verified our theories for a deformation of the Gaussian model, and described dynamical evolution of flat metrics for Kerr and Reissner-Nordstr\"om black holes.