Showing 2024Show all
3 papers · 1 filter
cs.LG2024
Adaptive teachers for amortized samplers
Minsu Kim, Sanghyeok Choi, Taeyoung Yun +7
Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnormalized density where exact sampling is in…
cs.LG2024
Pessimistic Backward Policy for GFlowNets
Hyosoon Jang, Yunhui Jang, Minsu Kim +2
This paper studies Generative Flow Networks (GFlowNets), which learn to sample objects proportionally to a given reward function through the trajectory of state transitions. In thi…
cs.LG2024
Improved off-policy training of diffusion samplers
Marcin Sendera, Minsu Kim, Sarthak Mittal +6
We study the problem of training diffusion models to sample from a distribution with a given unnormalized density or energy function. We benchmark several diffusion-structured infe…