4 papers
Sparse Signal Recovery using Log-Sum Regularization and Adaptive Smoothing
Keisuke Morita, Masayuki Ohzeki
We study sparse signal recovery from noisy linear observations using nonconvex log-sum regularization. The log-sum penalty reduces the shrinkage bias of regularization and…
Phase transition in compressed sensing using log-sum penalty and adaptive smoothing
Keisuke Morita, Federico Ricci-Tersenghi, Masayuki Ohzeki
In many real-world problems, recovering sparse signals from underdetermined linear systems remains a fundamental challenge. Although norm minimization is widely used, it s…
Filtering out mislabeled training instances using black-box optimization and quantum annealing
Makoto Otsuka, Kento Kodama, Keisuke Morita +1
This study proposes an approach for removing mislabeled instances from contaminated training datasets by combining surrogate model-based black-box optimization (BBO) with postproce…
Solution space and storage capacity of fully connected two-layer neural networks with generic activation functions
Sota Nishiyama, Masayuki Ohzeki
The storage capacity of a binary classification model is the maximum number of random input-output pairs per parameter that the model can learn. It is one of the indicators of the…