From the 1 of 7 linked papers with an AI index.
7 papers
Adaptive Score-Based VAMP: Self-Tuning Hyperparameters via Tilted EM
Siqi Na, Tadashi Wadayama
The paper proposes an adaptive version of score‑based vector approximate message passing (SC‑VAMP) that automatically tunes hyperparameters using a local tilted EM step, achieving…
Differentiable Conditional Mutual Information for Multi-Terminal Linear Gaussian Wireless Networks
Tadashi Wadayama, Siqi Na
The rate regions of multi-terminal Gaussian channels (multiple-access, broadcast, interference, relay) are delimited by conditional mutual informations among g…
LLM-Steered Power Allocation for Parallel QPSK-AWGN Channels
Tadashi Wadayama
Large language models (LLMs) are increasingly being explored as high-level decision modules in closed-loop systems, but their stochastic nature makes safe integration challenging.…
Three-Module SC-VAMP for LDPC-Coded Nonlinear Channels
Tadashi Wadayama, Takumi Takahashi
We propose a three-module extension of score-based VAMP (SC-VAMP) for signal recovery in nonlinear channels, where the received signal is obtained by applying a nonlinearity to a l…
Score-Based VAMP with Fisher-Information-Based Onsager Correction
Tadashi Wadayama, Takumi Takahashi
We propose score-based VAMP (SC-VAMP), a variant of vector approximate message passing (VAMP) in which the Onsager correction is expressed and computed via conditional Fisher infor…
Physics-Aware Sparse Signal Recovery Through PDE-Governed Measurement Systems
Tadashi Wadayama, Koji Igarashi, Takumi Takahashi
This paper introduces a novel framework for physics-aware sparse signal recovery in measurement systems governed by partial differential equations (PDEs). Unlike conventional compr…