Showing 2023Show all
2 papers · 1 filter
math.OC2023
Proximal Diagonal Newton Methods for Composite Optimization Problems
Shotaro Yagishita, Shummin Nakayama
This paper proposes new proximal Newton-type methods with a diagonal metric for solving composite optimization problems whose objective function is the sum of a twice continuously…
stat.ME2023
Outlier-robust neural network training: variation regularization meets trimmed loss to prevent functional breakdown
Akifumi Okuno, Shotaro Yagishita
In this study, we tackle the challenge of outlier-robust predictive modeling using highly expressive neural networks. Our approach integrates two key components: (1) a transformed…