English
Related papers

Related papers: Improved off-policy training of diffusion samplers

200 papers

We explain how to use diffusion models to learn inverse renormalization group flows of statistical and quantum field theories. Diffusion models are a class of machine learning models which have been used to generate samples from complex…

High Energy Physics - Theory · Physics 2023-09-07 Jordan Cotler , Semon Rezchikov

Drawing from the theory of stochastic differential equations, we introduce a novel sampling method for known distributions and a new algorithm for diffusion generative models with unknown distributions. Our approach is inspired by the…

Statistics Theory · Mathematics 2024-07-12 Xicheng Zhang

Score-based models generate samples by mapping noise to data (and vice versa) via a high-dimensional diffusion process. We question whether it is necessary to run this entire process at high dimensionality and incur all the inconveniences…

Machine Learning · Computer Science 2023-02-28 Bowen Jing , Gabriele Corso , Renato Berlinghieri , Tommi Jaakkola

This paper presents a novel theoretical framework for understanding how diffusion models can learn disentangled representations. Within this framework, we establish identifiability conditions for general disentangled latent variable models,…

Reinforcement learning (RL) algorithms are often categorized as either on-policy or off-policy depending on whether they use data from a target policy of interest or from a different behavior policy. In this paper, we study a subtle…

Machine Learning · Computer Science 2022-10-12 Rujie Zhong , Duohan Zhang , Lukas Schäfer , Stefano V. Albrecht , Josiah P. Hanna

A key task in Artificial Intelligence is learning effective policies for controlling agents in unknown environments to optimize performance measures. Off-policy learning methods, like Q-learning, allow learners to make optimal decisions…

Artificial Intelligence · Computer Science 2025-09-10 Mingxuan Li , Junzhe Zhang , Elias Bareinboim

Learning to sample from intractable distributions over discrete sets without relying on corresponding training data is a central problem in a wide range of fields, including Combinatorial Optimization. Currently, popular deep learning-based…

Machine Learning · Computer Science 2025-08-25 Sebastian Sanokowski , Sepp Hochreiter , Sebastian Lehner

Exploration and adaptation to new tasks in a transfer learning setup is a central challenge in reinforcement learning. In this work, we build on the idea of modeling a distribution over policies in a Bayesian deep reinforcement learning…

Machine Learning · Computer Science 2019-06-11 Disha Shrivastava , Eeshan Gunesh Dhekane , Riashat Islam

Diffusion models have seen tremendous success as generative architectures. Recently, they have been shown to be effective at modelling policies for offline reinforcement learning and imitation learning. We explore using diffusion as a model…

Machine Learning · Computer Science 2025-11-04 Liam Schramm , Abdeslam Boularias

Learning from observation (LfO) aims to imitate experts by learning from state-only demonstrations without requiring action labels. Existing adversarial imitation learning approaches learn a generator agent policy to produce state…

Machine Learning · Computer Science 2024-10-10 Bo-Ruei Huang , Chun-Kai Yang , Chun-Mao Lai , Dai-Jie Wu , Shao-Hua Sun

Probabilistic regression models the entire predictive distribution of a response variable, offering richer insights than classical point estimates and directly allowing for uncertainty quantification. While diffusion-based generative models…

Machine Learning · Computer Science 2025-10-07 Carlo Kneissl , Christopher Bülte , Philipp Scholl , Gitta Kutyniok

Despite the remarkable generation capabilities of Diffusion Models (DMs), conducting training and inference remains computationally expensive. Previous works have been devoted to accelerating diffusion sampling, but achieving data-efficient…

Computer Vision and Pattern Recognition · Computer Science 2024-10-03 Yize Li , Yihua Zhang , Sijia Liu , Xue Lin

In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy using logged trajectory data generated from a different behavior policy, without execution of the target policy.…

Machine Learning · Computer Science 2022-11-04 Jie Wang , Rui Gao , Hongyuan Zha

Flow-based generative models, including diffusion models, excel at modeling continuous distributions in high-dimensional spaces. In this work, we introduce Flow Policy Optimization (FPO), a simple on-policy reinforcement learning algorithm…

Machine Learning · Computer Science 2025-08-04 David McAllister , Songwei Ge , Brent Yi , Chung Min Kim , Ethan Weber , Hongsuk Choi , Haiwen Feng , Angjoo Kanazawa

Diffusion models have become increasingly popular for generative modeling due to their ability to generate high-quality samples. This has unlocked exciting new possibilities for solving inverse problems, especially in image restoration and…

Generative diffusion models synthesize new samples by reversing a diffusive process that converts a given data set to generic noise. This is accomplished by training a neural network to match the gradient of the log of the probability…

Machine Learning · Computer Science 2023-10-11 Akhil Premkumar

Generative models such as denoising diffusion models are quickly advancing their ability to approximate highly complex data distributions. They are also increasingly leveraged in scientific machine learning, where samples from the implied…

Machine Learning · Computer Science 2025-03-14 Jan-Hendrik Bastek , WaiChing Sun , Dennis M. Kochmann

Solving ill-posed inverse problems requires careful formulation of prior beliefs over the signals of interest and an accurate description of their manifestation into noisy measurements. Handcrafted signal priors based on e.g. sparsity are…

Machine Learning · Computer Science 2025-08-14 Tristan S. W. Stevens , Hans van Gorp , Faik C. Meral , Junseob Shin , Jason Yu , Jean-Luc Robert , Ruud J. G. van Sloun

This paper proposes a supervised training algorithm for learning stochastic resource allocation policies with generative diffusion models (GDMs). We formulate the allocation problem as the maximization of an ergodic utility function subject…

Machine Learning · Computer Science 2025-09-23 Yigit Berkay Uslu , Samar Hadou , Shirin Saeedi Bidokhti , Alejandro Ribeiro

Inverse problems aim to determine parameters from observations, a crucial task in engineering and science. Lately, generative models, especially diffusion models, have gained popularity in this area for their ability to produce realistic…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Gabriel della Maggiora , Luis Alberto Croquevielle , Nikita Deshpande , Harry Horsley , Thomas Heinis , Artur Yakimovich