3 papers
cs.LG2026
Noise Schedule Design for Diffusion Models: An Optimal Control Perspective
Seo Taek Kong, Weina Wang, R. Srikant
We develop a principled framework for analyzing and designing noise schedules in diffusion models. We show that one can recast this design problem as an optimal control problem, wh…
cs.LG2026
Provably Convergent Primal-Dual DPO for Constrained LLM Alignment
Yihan Du, Seo Taek Kong, R. Srikant
The widespread application of large language models (LLMs) raises increasing demands on ensuring safety or imposing constraints, such as reducing harmful content and adhering to pr…
cs.LG2025
Nonasymptotic CLT and Error Bounds for Two-Time-Scale Stochastic Approximation
Seo Taek Kong, Sihan Zeng, Thinh T. Doan +1
We consider linear two-time-scale stochastic approximation algorithms driven by martingale noise. Recent applications in machine learning motivate the need to understand finite-tim…