Browsing by Subject "Machine Learning, Retrieval Augmentation, Benign Overfitting, Long Tail Theory, Simplicity Bias, Natural Language Processing, Memorization and Generalization, Learning Theory"

Now showing items 1-1 of 1

BENIGN OVERFITTING WITH RETRIEVAL AUGMENTED MODELS

Assylbekov, Zhenisbek; Tezekbayev, Maxat; Nikoulina, Vassilina; Gallé, Matthias (Nazarbayev University School of Sciences and Humanities, 2022)

Despite the fact that modern deep neural networks have the ability to memorize (almost) the entire training set they generalize well to unseen data, contradicting traditional learning theory. This phenomenon --- dubbed ...