Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Multi-Step Alignment as Markov Games: An Optimistic Online Gradient Descent Approach with Convergence Guarantees
Yongtao Wu, Luca Viano, Yihang Chen +4
Reinforcement Learning from Human Feedback (RLHF) has been highly successful in aligning large language models with human preferences. While prevalent methods like DPO have demonst…
cs.LG2024
Generalization of Scaled Deep ResNets in the Mean-Field Regime
Yihang Chen, Fanghui Liu, Yiping Lu +2
Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate \…