Search Results for author:
Found 2 papers, 0 papers with code
Adaptive Label Smoothing with Self-Knowledge
Overconfidence has been shown to impair generalization and calibration of a neural network.
SeqPATE: Differentially Private Text Generation via Knowledge Distillation
Differentially private (DP) learning algorithms provide guarantees on identifying the existence of a training sample from model outputs.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
