3 papers
cs.LG2026
When Errors Can Be Beneficial: A Categorization of Imperfect Rewards for Policy Gradient
Shuning Shang, Hubert Strauss, Stanley Wei +2
Training language models via reinforcement learning often relies on imperfect proxy rewards, since ground truth rewards that precisely define the intended behavior are rarely avail…
cs.LG2024
Initialization Matters: On the Benign Overfitting of Two-Layer ReLU CNN with Fully Trainable Layers
Shuning Shang, Xuran Meng, Yuan Cao +1
Benign overfitting refers to how over-parameterized neural networks can fit training data perfectly and generalize well to unseen data. While this has been widely investigated theo…
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…