4 papers · 1 filter
Sharp Convergence and Sampling Trade-offs for Riemannian Diffusion under Nonnegative Ricci Curvature
Yuhao Liu, Longbo Huang
Diffusion models have emerged as state-of-the-art generative models, with recent extensions from Euclidean spaces to Riemannian manifolds. However, existing convergence guarantees…
Lipschitz Bandits with Arbitrary Feedback Delays
Yuhao Liu, Yu Chen, Longbo Huang
The Lipschitz bandit problem extends the traditional multi-armed bandit framework to continuous action spaces by assuming that the reward functions satisfy a Lipschitz condition. T…
When Context Returns: Toward Robust Internalization in On-Policy Distillation
Xun Wang, Ruishuo Chen, Zhuoran Li +2
Recent work has shown that on-policy distillation can internalize privileged context, such as system prompts or task hints, into a student model so that the context is no longer ne…
Best-of-Both-Worlds for Heavy-Tailed Markov Decision Processes
Yu Chen, Yuhao Liu, Jiatai Huang +2
We investigate episodic Markov Decision Processes with heavy-tailed losses (HTMDPs). Existing approaches for HTMDPs are conservative in stochastic environments and lack adaptivity…