collaborators

9 papers

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…