Showing 2024Show all
2 papers · 1 filter
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…
stat.ML2024
Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalization
Yutong Wang, Rishi Sonthalia, Wei Hu
We study the generalization capability of nearly-interpolating linear regressors: 's whose training error is positive but small, i.e., below the noise floor. Unde…