collaborators

6 papers

eess.SP2026

Theoretical Validation of the Latent Optimally Partitioned- Penalty with Application to Angular Power Spectrum Estimation

Hiroki Kuroda, Renato Luis Garrido Cavalcante, Masahiro Yukawa

This paper demonstrates that, in both theory and practice, the latent optimally partitioned (LOP)- penalty is effective for exploiting block-sparsity without knowled…

cs.LG2026

Nonconvex Latent Optimally Partitioned Block-Sparse Recovery via Log-Sum and Minimax Concave Penalties

Takanobu Furuhashi, Hiroki Kuroda, Masahiro Yukawa +3

We propose two nonconvex regularization methods, LogLOP-l2/l1 and AdaLOP-l2/l1, for recovering block-sparse signals with unknown block partitions. These methods address the underes…

math.OC2025

Plugging Weight-tying Nonnegative Neural Network into Proximal Splitting Method: Architecture for Guaranteeing Convergence to Optimal Point

Haruya Shimizu, Masahiro Yukawa

We propose a novel multi-layer neural network architecture that gives a promising neural network empowered optimization approach to the image restoration problem. The proposed arch…

math.OC2025

Monotone Lipschitz-Gradient Denoiser: Explainability of Operator Regularization Approaches Free From Lipschitz Constant Control

Masahiro Yukawa, Isao Yamada

This paper addresses explainability of the operator-regularization approach under the use of monotone Lipschitz-gradient (MoL-Grad) denoiser -- an operator that can be expressed as…

math.OC2025

Continuous Relaxation of Discontinuous Shrinkage Operator: Proximal Inclusion and Conversion

Masahiro Yukawa

We present a principled way of deriving a continuous relaxation of a given discontinuous shrinkage operator, which is based on two fundamental results, proximal inclusion and conve…

cs.LG2025

Federated Smoothing ADMM for Localization

Reza Mirzaeifard, Ashkan Moradi, Masahiro Yukawa +1

This paper addresses the challenge of localization in federated settings, which are characterized by distributed data, non-convexity, and non-smoothness. To tackle the scalability…