6 papers
A Differentiable Covariance Calculus for Linear Gaussian Bayesian Networks
Tadashi Wadayama
Linear Gaussian Bayesian networks, equivalently linear Gaussian structural equation models, recur across statistics, control, and communications; in the vector-valued setting that…
Mutual Information Optimization via K-Recursion and Automatic Differentiation for Linear Gaussian Wireless Networks
Tadashi Wadayama, Na Siqi
We present a differentiable framework for end-to-end mutual information (MI) optimization over linear Gaussian directed acyclic graphs (DAGs). The framework targets network-wide de…
Physics-Aware Linearized ADMM and Its Unrolling
Satoshi Takabe, Shunta Arai, Tadashi Wadayama
Recently, partial differential equations (PDEs) have been used to directly model the measurement process in signal processing, although their evaluation is costly. In this paper, w…
Information Gradient for Directed Acyclic Graphs: A Score-based Framework for End-to-End Mutual Information Maximization
Tadashi Wadayama
This paper presents a general framework for end-to-end mutual information maximization in communication and sensing systems represented by stochastic directed acyclic graphs (DAGs)…
Mutual Information Estimation via Score-to-Fisher Bridge for Nonlinear Gaussian Noise Channels
Tadashi Wadayama
We present a numerical method to evaluate mutual information (MI) in nonlinear Gaussian noise channels by using denoising score matching (DSM) learning for estimating the score fun…
Information Gradient for Nonlinear Gaussian Channel with Applications to Task-Oriented Communication
Tadashi Wadayama
We propose a gradient-based framework for optimizing parametric nonlinear Gaussian channels via mutual information maximization. Leveraging the score-to-Fisher bridge (SFB) methodo…