5 papers
ProACT: Towards Breakdown-Aware Proactive Agent in Multi-User Collaboration
Shu Yang, Difei Xu, Jiaxin Pei +1
Conversational agents are increasingly embedded in human collaborative work, yet they remain fundamentally passive and reactive: they respond to explicit user requests rather than…
Differentially Private Non-convex Distributionally Robust Optimization
Difei Xu, Meng Ding, Zebin Ma +4
Real-world deployments routinely face distribution shifts, group imbalances, and adversarial perturbations, under which the traditional Empirical Risk Minimization (ERM) framework…
Finding Differentially Private Second Order Stationary Points in Stochastic Minimax Optimization
Difei Xu, Youming Tao, Meng Ding +2
We provide the first study of the problem of finding differentially private (DP) second-order stationary points (SOSP) in stochastic (non-convex) minimax optimization. Existing lit…
Beyond Ordinary Lipschitz Constraints: Differentially Private Stochastic Optimization with Tsybakov Noise Condition
Difei Xu, Meng Ding, Zihang Xiang +2
We study Stochastic Convex Optimization in the Differential Privacy model (DP-SCO). Unlike previous studies, here we assume the population risk function satisfies the Tsybakov Nois…
Towards User-level Private Reinforcement Learning with Human Feedback
Jiaming Zhang, Mingxi Lei, Meng Ding +5
Reinforcement Learning with Human Feedback (RLHF) has emerged as an influential technique, enabling the alignment of large language models (LLMs) with human preferences. Despite th…