2 papers
cs.LG2026
Improving scalable oversight with co-trained monitors
Joseph H. Rudoler, Kevin Tan, Benedict Tessler +2
Worker-monitor setups are a promising approach to AI oversight, but training workers against fixed monitors can incentivize monitor evasion. We study whether this failure mode can…
stat.ML2026
Estimating Implicit Regularization in Deep Learning
Joseph H. Rudoler, Kevin Tan, Giles Hooker +1
Deep learning systems are known to exhibit implicit regularization (alt. implicit bias), favoring simple solutions instead of merely minimizing the loss function. In some cases, we…