3 papers
cs.LG2026
Minimax-Optimal Predictive Flow Matching under Distribution Drift
Aadithya Srikanth, Vaneet Aggarwal
Flow matching learns a generative velocity field by regression, but under distribution drift a field must be deployed before the current data arrive. We study this predictive probl…
cs.LG2025
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.LG2023
Insights into Closed-form IPM-GAN Discriminator Guidance for Diffusion Modeling
Aadithya Srikanth, Siddarth Asokan, Nishanth Shetty +1
Diffusion models are a state-of-the-art generative modeling framework that transform noise to images via Langevin sampling, guided by the score, which is the gradient of the logari…