2 papers
cs.LG2026
On the optimization dynamics of RLVR: Gradient gap and step size thresholds
Joe Suk, Yaqi Duan
Reinforcement Learning with Verifiable Rewards (RLVR), which uses simple binary feedback to post-train large language models, has found significant empirical success. However, a pr…
stat.ML2025
Adaptive Smooth Non-Stationary Bandits
Joe Suk
We study a -armed non-stationary bandit model where rewards change smoothly, as captured by Hölder class assumptions on rewards as functions of time. Such smooth changes are pa…