3 papers
cs.LG2025
ReDiF: Reinforced Distillation for Few Step Diffusion
Amirhossein Tighkhorshid, Zahra Dehghanian, Gholamali Aminian +2
Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In thi…
cs.LG2025
Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning
Armin Behnamnia, Gholamali Aminian, Alireza Aghaei +3
Off-policy learning and evaluation leverage logged bandit feedback datasets, which contain context, action, propensity score, and feedback for each data point. These scenarios face…
cs.LG2025
Semi-pessimistic Reinforcement Learning
Jin Zhu, Xin Zhou, Jiaang Yao +5
Offline reinforcement learning (RL) aims to learn an optimal policy from pre-collected data. However, it faces challenges of distributional shift, where the learned policy may enco…