Zobrazeno 1 - 10
of 568
pro vyhledávání: '"Wei Yuting"'
The denoising diffusion probabilistic model (DDPM) has emerged as a mainstream generative model in generative AI. While sharp convergence guarantees have been established for the DDPM, the iteration complexity is, in general, proportional to the ambi
Externí odkaz:
http://arxiv.org/abs/2410.18784
Statistical inference with finite-sample validity for the value function of a given policy in Markov decision processes (MDPs) is crucial for ensuring the reliability of reinforcement learning. Temporal Difference (TD) learning, arguably the most wid
Externí odkaz:
http://arxiv.org/abs/2410.16106
Diffusion models play a pivotal role in contemporary generative modeling, claiming state-of-the-art performance across various domains. Despite their superior sample quality, mainstream diffusion-based stochastic samplers like DDPM often require a la
Externí odkaz:
http://arxiv.org/abs/2410.04760
Hybrid Reinforcement Learning (RL), where an agent learns from both an offline dataset and online explorations in an unknown environment, has garnered significant recent interest. A crucial question posed by Xie et al. (2022) is whether hybrid RL can
Externí odkaz:
http://arxiv.org/abs/2408.04526
Diffusion models, which convert noise into new data instances by learning to reverse a diffusion process, have become a cornerstone in contemporary generative modeling. In this work, we develop non-asymptotic convergence theory for a popular diffusio
Externí odkaz:
http://arxiv.org/abs/2408.02320
Autor:
Wei, Yuting, Xu, Yuanxing, Wei, Xinru, Yang, Simin, Zhu, Yangfu, Li, Yuqing, Liu, Di, Wu, Bin
Given the importance of ancient Chinese in capturing the essence of rich historical and cultural heritage, the rapid advancements in Large Language Models (LLMs) necessitate benchmarks that can effectively evaluate their understanding of ancient cont
Externí odkaz:
http://arxiv.org/abs/2403.06574
Score-based diffusion models, while achieving remarkable empirical performance, often suffer from low sampling speed, due to extensive function evaluations needed during the sampling phase. Despite a flurry of recent activities towards speeding up di
Externí odkaz:
http://arxiv.org/abs/2403.03852
Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties. Such information is coined as guidance. For example, in text-to-image synthesis, text input is
Externí odkaz:
http://arxiv.org/abs/2403.01639
Consistency models, which were proposed to mitigate the high computational overhead during the sampling phase of diffusion models, facilitate single-step sampling while attaining state-of-the-art empirical performance. When integrated into the traini
Externí odkaz:
http://arxiv.org/abs/2402.07802
Autor:
Li, Gen, Wei, Yuting
Characterizing the distribution of high-dimensional statistical estimators is a challenging task, due to the breakdown of classical asymptotic theory in high dimension. This paper makes progress towards this by developing non-asymptotic distributiona
Externí odkaz:
http://arxiv.org/abs/2401.03923