Noisy-Label Loss Correction

Correct expected classification risk under a known label-noise channel and expose its singular limit.

Experiment

In the interactive module at https://riano.app/module/noisy-label-loss-correction, you can investigate how expected loss and corrected loss change under symmetric label noise.

1. Select a value from the "Flip probability" control to update the label noise transition matrix. Notice that choosing 0.5 demonstrates the singular matrix boundary case, rendering backward correction unavailable.
2. Select a different value from the "Predicted clean probability" control to observe the updated target loss and observe how the backward corrected expected loss relates to the clean loss.