NeurIPS 2025poster0 citations
Energy-based generator matching: A neural sampler for general state space
Dongyeop Woo, Minsu Kim, Minkyu Kim, Kiyoung Seong, Sungsoo Ahn
Abstract
We propose Energy-based generator matching (EGM), a modality-agnostic approach to train generative models from energy functions in the absence of data. Extending the recently proposed generator matching, EGM enables training of arbitrary continuous-time Markov processes, e.g., diffusion, flow, and jump, and can generate data from continuous, discrete, and a mixture of two modalities. To this end, we propose estimating the generator matching loss using self-normalized importance sampling with an additional bootstrapping trick to reduce variance in the importance weight. We validate EGM on both discrete and multimodal tasks up to 100 and 20 dimensions, respectively.
neural samplerBoltzmann distributionsdiffusion modelflow model
BibTeX
@inproceedings{
woo2025energybased,
title={Energy-based generator matching: A neural sampler for general state space},
author={Dongyeop Woo and Minsu Kim and Minkyu Kim and Kiyoung Seong and Sungsoo Ahn},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=UKJkad8aUF}
}