2 citations · 5 across the 22 of their papers we have counts for
3 papers · 1 filter
Discrete Langevin-Inspired Posterior Sampling
Chaitanya Amballa, Sattwik Basu, Jorge Vančo Sampedro +1
We study posterior sampling for inverse problems in discrete state spaces using discrete diffusion models as generative priors. While continuous diffusion models have become widely…
Learning Energy-based Variational Latent Prior for VAEs
Debottam Dutta, Chaitanya Amballa, Zhongweiyang Xu +2
Variational Auto-Encoders (VAEs) are known to generate blurry and inconsistent samples. One reason for this is the "prior hole" problem. A prior hole refers to regions that have hi…
Kernel Learning for Sample Constrained Black-Box Optimization
Rajalaxmi Rajagopalan, Yu-Lin Wei, Romit Roy Choudhury
Black box optimization (BBO) focuses on optimizing unknown functions in high-dimensional spaces. In many applications, sampling the unknown function is expensive, imposing a tight…