9 papers
Hypergradient-based Bilevel Reinforcement Learning with Improved Sample Complexity
Naman Saxena, Mudit Gaur, Vaneet Aggarwal
Bilevel reinforcement learning (RL) is an important framework within the literature of RL that can be used to formalize various categories of problems, such as meta-learning, hiera…
Discrete State Diffusion Models: A Sample Complexity Perspective
Aadithya Srikanth, Mudit Gaur, Vaneet Aggarwal
Diffusion models have demonstrated remarkable performance in generating high-dimensional samples across domains such as vision, language, and the sciences. Although continuous-stat…
Improved Sample Complexity For Diffusion Model Training Without Empirical Risk Minimizer Access
Mudit Gaur, Prashant Trivedi, Sasidhar Kunapuli +2
Diffusion models have demonstrated state-of-the-art performance across vision, language, and scientific domains. Despite their empirical success, prior theoretical analyses of the…
Oracle-Robust Online Alignment for Large Language Models
Zimeng Li, Mudit Gaur, Vaneet Aggarwal
We study online alignment of large language models under misspecified preference feedback, where the observed preference oracle deviates from an ideal but unknown ground-truth orac…
On The Sample Complexity Bounds In Bilevel Reinforcement Learning
Mudit Gaur, Utsav Singh, Amrit Singh Bedi +2
Bilevel reinforcement learning (BRL) has emerged as a powerful framework for aligning generative models, yet its theoretical foundations, especially sample complexity bounds, remai…
Order-Optimal Sample Complexity of Rectified Flows
Hari Krishna Sahoo, Mudit Gaur, Vaneet Aggarwal
Recently, flow-based generative models have shown superior efficiency compared to diffusion models. In this paper, we study rectified flow models, which constrain transport traject…