3 papers
cs.LG2026
CT-OT Flow: Estimating Continuous-Time Dynamics from Discrete Temporal Snapshots
Keisuke Kawano, Takuro Kutsuna, Naoki Hayashi +2
In many real-world settings--e.g., single-cell RNA sequencing, mobility sensing, and environmental monitoring--data are observed only as temporally aggregated snapshots collected o…
cs.LG2025
Minimal Sufficient Views: A DNN model making predictions with more evidence has higher accuracy
Keisuke Kawano, Takuro Kutsuna, Keisuke Sano
Deep neural networks (DNNs) exhibit high performance in image recognition; however, the reasons for their strong generalization abilities remain unclear. A plausible hypothesis is…
cs.LG2025
Accuracy-Preserving Calibration via Statistical Modeling on Probability Simplex
Yasushi Esaki, Akihiro Nakamura, Keisuke Kawano +2
Classification models based on deep neural networks (DNNs) must be calibrated to measure the reliability of predictions. Some recent calibration methods have employed a probabilist…