MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control
By: Yuchen Zhu , Wei Guo , Jaemoo Choi and more
Potential Business Impact:
Creates computer programs that guess better from many choices.
We study the problem of learning a neural sampler to generate samples from discrete state spaces where the target probability mass function $\pi\propto\mathrm{e}^{-U}$ is known up to a normalizing constant, which is an important task in fields such as statistical physics, machine learning, combinatorial optimization, etc. To better address this challenging task when the state space has a large cardinality and the distribution is multi-modal, we propose $\textbf{M}$asked $\textbf{D}$iffusion $\textbf{N}$eural $\textbf{S}$ampler ($\textbf{MDNS}$), a novel framework for training discrete neural samplers by aligning two path measures through a family of learning objectives, theoretically grounded in the stochastic optimal control of the continuous-time Markov chains. We validate the efficiency and scalability of MDNS through extensive experiments on various distributions with distinct statistical properties, where MDNS learns to accurately sample from the target distributions despite the extremely high problem dimensions and outperforms other learning-based baselines by a large margin. A comprehensive study of ablations and extensions is also provided to demonstrate the efficacy and potential of the proposed framework.
Similar Papers
Proximal Diffusion Neural Sampler
Machine Learning (CS)
Helps computers draw complex pictures by learning step-by-step.
Causal Negative Sampling via Diffusion Model for Out-of-Distribution Recommendation
Machine Learning (CS)
Makes online suggestions more accurate and fair.
Optimal Inference Schedules for Masked Diffusion Models
Machine Learning (CS)
Makes AI write faster by guessing words out of order.