18 citations · 25 across the 8 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Actually, All Learnable Distribution Classes Are Privately Learnable
Mohammad Afzali, Hassan Ashtiani, Alex Bie +4
We show that every class of distributions that is learnable up to arbitrarily small target error in total variation distance with finitely many samples is also learnable under ($\v…
cs.LG2026
SimHack: Predicting the onset of detectable reward hacking before RL training
Junwei Deng, Alex Bie, Natalia Ponomareva
When training LLMs to code with reinforcement learning, reward hacking is often detectable but difficult to prevent, since (a) environment hardening is increasingly difficult as tr…