paper-with-me

Papers

From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster training

2025-01-10 · Julius Berner, Lorenz Richter, Marcin Sendera, Jarrid Rector-Brooks, Nikolay Malkin

We study the problem of training neural stochastic differential equations, or diffusion models, to sample from a Boltzmann distribution without access to target samples. Existing methods for training such models enforce time-reversal of the generative and noising processes, using either differentiable simulation or off-policy reinforcement learning (RL). We prove equivalences between families of objectives in the limit of infinitesimal discretization steps, linking entropic RL methods (GFlowNets) with continuous-time objects (partial differential equations and path space measures). We further show that an appropriate choice of coarse time discretization during training allows greatly improved sample efficiency and the use of time-local objectives, achieving competitive performance on standard sampling benchmarks with reduced computational cost.

📄 PDF Abstract BibTeX arXiv:2501.06148

Code (1)

gfnorg/gfn-diffusion 공식 구현 pytorch

Tasks

Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Reinforcement Learning for Continuous-Time Jump Markov Decision Processes with Applications to Network Dynamic Pricing

2026-08-21 · Huiling Meng, Ningyuan Chen, Xuefeng Gao arxiv

We study reinforcement learning (RL) in Continuous-Time Jump Markov Decision Processes (CTJMDPs) featuring general discrete state spaces (which need not possess a vector space structure) and continuous/discrete action sp…

Reinforcement Learning

CHDP: Cooperative Hybrid Diffusion Policies for Reinforcement Learning in Parameterized Action Space

2026-01-09 · Bingyi Liu, Jinbo He, Haiyong Shi, Enshu Wang 외 arxiv

Hybrid action space, which combines discrete choices and continuous parameters, is prevalent in domains such as robot control and game AI. However, efficiently modeling and optimizing hybrid discrete-continuous action sp…

Reinforcement Learning

Policy Gradient Guidance Enables Test Time Control

2025-10-02 · Jianing Qi, Hao Tang, Zhigang Zhu arxiv

We introduce Policy Gradient Guidance (PGG), a simple extension of classifier-free guidance from diffusion models to classical policy gradient methods. PGG augments the policy gradient with an unconditional branch and in…

Reinforcement LearningContinuous Control

Discrete-state Continuous-time Diffusion for Graph Generation

2024-05-19 · Zhe Xu, Ruizhong Qiu, Yuzhong Chen, Huiyuan Chen 외

Graph is a prevalent discrete data structure, whose generation has wide applications such as drug discovery and circuit design. Diffusion generative models, as an emerging research focus, have been applied to graph gener…

Drug DiscoveryGraph Generation

Cometh: A continuous-time discrete-state graph diffusion model

2024-06-10 · Antoine Siraudin, Fragkiskos D. Malliaros, Christopher Morris

Discrete-state denoising diffusion models led to state-of-the-art performance in graph generation, especially in the molecular domain. Recently, they have been transposed to continuous time, allowing more flexibility in …

DenoisingGraph Generation