https://nalar.dev/tags/label-smoothing/ Recent content in Label Smoothing on Nalar Hugo en-us Thu, 24 Sep 2026 00:00:00 +0000 https://nalar.dev/label-smoothing-redistributes-target-probability-across-classes/ Thu, 24 Sep 2026 00:00:00 +0000 https://nalar.dev/label-smoothing-redistributes-target-probability-across-classes/ <p>A classifier trained with one-hot targets assigns all target probability mass to one class. Label smoothing changes that target before cross-entropy is evaluated: some mass is moved away from the designated class and assigned to other classes. The network architecture can remain identical, yet the optimization objective is no longer the same.</p> <p>That distinction matters when interpreting confidence, loss values, and implementation settings. Label smoothing is not a post-processing operation on predicted probabilities. It changes the target distribution used to produce the training signal.</p>