2 papers
cs.LG2026
Let's Ask Gauss: Improved One-Run Privacy Auditing
Adya Agrawal, Yu Wei, Jaspal Singh +2
Privacy auditing provides an important safeguard by estimating the actual information leaked by a model, thus ensuring that theoretical privacy guarantees hold in practice. We stud…
cs.LG2025
Near-Optimal Sample Complexity Bounds for Constrained Average-Reward MDPs
Yukuan Wei, Xudong Li, Lin F. Yang
Recent advances have significantly improved our understanding of the sample complexity of learning in average-reward Markov decision processes (AMDPs) under the generative model. H…