In human pedagogy, teachers and students can interact adaptively to maximize communication efficiency. Theteacher adjusts herteaching method fordifferent students, and the student, after getting familiar with the teacher's instruction mechanism,caninfertheteacher'sintentiontolearnfaster.

Quitesurprisingly, we show that the convergence speed of the training loss controls the magnitude of the biasing effect: the slower the convergence, the better the bias.

A prime example is single-cell RNA sequencing (scRNA-seq) data (Figure 1).

Online multiclass classification is a ubiquitous problem in machine learning.