Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Correcting or Continuing? What On-Policy Distillation Learns from Student Errors
Shuo Yang, Zheyu Zhang, Mahito Sugiyama +1
On-policy distillation (OPD) trains a student on its own rollouts under a frozen teacher, mitigating the distribution mismatch of off-policy supervision. While prior work has prima…
cs.LG2024
Pseudo-Nonlinear Data Augmentation: A Constrained Energy Minimization Viewpoint
Pingbang Hu, Mahito Sugiyama
We propose a simple yet novel data augmentation method for general data modalities based on energy-based modeling and principles from information geometry. Unlike most existing lea…