3 papers
cs.LG2024
Understanding In-Context Learning of Linear Models in Transformers Through an Adversarial Lens
Usman Anwar, Johannes Von Oswald, Louis Kirsch +2
In this work, we make two contributions towards understanding of in-context learning of linear models by transformers. First, we investigate the adversarial robustness of in-contex…
cs.LG2024
Benign Overfitting in Single-Head Attention
Roey Magen, Shuning Shang, Zhiwei Xu +3
The phenomenon of benign overfitting, where a trained neural network perfectly fits noisy training data but still achieves near-optimal test performance, has been extensively studi…
cs.LG2024
Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Context
Spencer Frei, Gal Vardi
Transformers have the capacity to act as supervised learning algorithms: by properly encoding a set of labeled training ("in-context") examples and an unlabeled test example into a…