paper-with-me

Papers

A theory of continuous generative flow networks

2023-01-30 · Salem Lahlou, Tristan Deleu, Pablo Lemos, Dinghuai Zhang, Alexandra Volokhova, Alex Hernández-García, Léna Néhale Ezzine, Yoshua Bengio, Nikolay Malkin

Generative flow networks (GFlowNets) are amortized variational inference algorithms that are trained to sample from unnormalized target distributions over compositional objects. A key limitation of GFlowNets until this time has been that they are restricted to discrete spaces. We present a theory for generalized GFlowNets, which encompasses both existing discrete GFlowNets and ones with continuous or hybrid state spaces, and perform experiments with two goals in mind. First, we illustrate critical points of the theory and the importance of various assumptions. Second, we empirically demonstrate how observations about discrete GFlowNets transfer to the continuous case and show strong results compared to non-GFlowNet baselines on several previously studied tasks. This work greatly widens the perspectives for the application of GFlowNets in probabilistic inference and various modeling settings.

📄 PDF Abstract BibTeX arXiv:2301.12594

Code (1)

saleml/continuous-gfn 공식 구현 pytorch

Tasks

Variational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

A Theory of Non-Acyclic Generative Flow Networks

2023-12-23 · Leo Maxime Brunswic, Yinchuan Li, Yushun Xu, Shangling Jui 외

GFlowNets is a novel flow-based method for learning a stochastic policy to generate objects via a sequence of actions and with probability proportional to a given positive reward. We contribute to relaxing hypotheses lim…

Combining Wasserstein-1 and Wasserstein-2 proximals: robust manifold learning via well-posed generative flows

2024-07-16 · Hyemin Gu, Markos A. Katsoulakis, Luc Rey-Bellet, Benjamin J. Zhang

We formulate well-posed continuous-time generative flows for learning distributions that are supported on low-dimensional manifolds through Wasserstein proximal regularizations of $f$-divergences. Wasserstein-1 proximal …

Monge-Ampère Flow for Generative Modeling

2018-09-26 · Linfeng Zhang, Weinan E, Lei Wang

We present a deep generative model, named Monge-Amp\`ere flow, which builds on continuous-time gradient flow arising from the Monge-Amp\`ere equation in optimal transport theory. The generative map from the latent space …

Density Estimation

Monge-Amp\`ere Flow for Generative Modeling

2019-05-01 · ICLR 2019 5 · Linfeng Zhang, Weinan E, Lei Wang

We present a deep generative model, named Monge-Amp\`ere flow, which builds on continuous-time gradient flow arising from the Monge-Amp\`ere equation in optimal transport theory. The generative map from the latent space …

Density Estimation

Flow-based sampling for multimodal and extended-mode distributions in lattice field theory

2021-07-01 · Daniel C. Hackett, Chung-Chun Hsieh, Sahil Pontula, Michael S. Albergo 외

Recent results have demonstrated that samplers constructed with flow-based generative models are a promising new approach for configuration generation in lattice field theory. In this paper, we present a set of training-…