no code implementations • 19 Oct 2022 • Yuki Tanaka, Shuhei M. Yoshida, Makoto Terao
A popular approach to this problem is first to train teacher models and then to use their confident predictions as pseudo ground-truth labels when training a student model.
1 code implementation • 4 Mar 2021 • Shuhei M. Yoshida, Takashi Takenouchi, Masashi Sugiyama
To this end, we derive a representation theorem for proper losses in supervised learning, which dualizes the Savage representation.