4 papers
Faster Diffusion Models via Higher-Order Approximation
Gen Li, Yuchen Zhou, Yuting Wei +1
In this paper, we explore provable acceleration of diffusion models without any additional retraining. Focusing on the task of approximating a target data distribution in $\mathbb{…
Transformers Meet In-Context Learning: A Universal Approximation Theory
Gen Li, Yuchen Jiao, Yu Huang +2
Large language models are capable of in-context learning, the ability to perform new tasks at test time using a handful of input-output examples, without parameter updates. We deve…
Statistical Inference for Policy Evaluation with Temporal Difference Learning
Weichen Wu, Gen Li, Yuting Wei +1
We investigate the statistical properties of Temporal Difference (TD) learning with Polyak-Ruppert averaging, arguably one of the most widely used algorithms in reinforcement learn…
A Sharp Convergence Theory for The Probability Flow ODEs of Diffusion Models
Gen Li, Yuting Wei, Yuejie Chi +1
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 wor…