Optimal Learners for Multiclass Problems thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Optimal Learners for Multiclass Problems

Published on Jul 15, 20142414 Views

The fundamental theorem of statistical learning states that for binary classification problems, any Empirical Risk Minimization (ERM) learning rule has close to optimal sample complexity. In this pape

Related categories