English
Related papers

Related papers: Variance reduction of diffusion model's gradients …

200 papers

Decentralized methods to solve finite-sum minimization problems are important in many signal processing and machine learning tasks where the data is distributed over a network of nodes and raw data sharing is not permitted due to privacy…

Machine Learning · Computer Science 2020-02-14 Ran Xin , Soummya Kar , Usman A. Khan

Diffusion models can be challenged in the low signal-to-noise regime, where they have to make pixel-level predictions despite the presence of high noise. The geometric intuition is akin to using the finest stroke for oil painting…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Yunwei Bai , Ying Kiat Tan , Yao Shu , Tsuhan Chen

Gradient-based methods are widely used to solve various optimization problems, however, they are either constrained by local optima dilemmas, simple convex constraints, and continuous differentiability requirements, or limited to…

Machine Learning · Computer Science 2026-03-19 Ming Li

Diffusion models have achieved remarkable success in text-to-image generation. However, their practical applications are hindered by the misalignment between generated images and corresponding text prompts. To tackle this issue,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Zijing Hu , Fengda Zhang , Long Chen , Kun Kuang , Jiahui Li , Kaifeng Gao , Jun Xiao , Xin Wang , Wenwu Zhu

We consider a class of parameter-dependent optimal control problems of elliptic PDEs with constraints of general type on the control variable. Applying the concept of variational discretization, [4], together with techniques from the…

Optimization and Control · Mathematics 2018-08-20 Ahmad Ahmad Ali , Michael Hinze

Scaling issues are mundane yet irritating for practitioners of reinforcement learning. Error scales vary across domains, tasks, and stages of learning; sometimes by many orders of magnitude. This can be detrimental to learning speed and…

Machine Learning · Computer Science 2021-05-13 Tom Schaul , Georg Ostrovski , Iurii Kemaev , Diana Borsa

We study optimal control of diffusions with slow and fast variables and address a question raised by practitioners: is it possible to first eliminate the fast variables before solving the optimal control problem and then use the optimal…

Optimization and Control · Mathematics 2014-06-16 Wei Zhang , Juan C. Latorre , Grigorios A. Pavliotis , Carsten Hartmann

The stochastic gradient descent (SGD) method is a widely used approach for solving stochastic optimization problems, but its convergence is typically slow. Existing variance reduction techniques, such as SAGA, improve convergence by…

Optimization and Control · Mathematics 2025-11-21 Fabio Nobile , Matteo Raviola , Nathan Schaeffer

This paper studies a distributed policy gradient in collaborative multi-agent reinforcement learning (MARL), where agents over a communication network aim to find the optimal policy to maximize the average of all agents' local returns. Due…

Multiagent Systems · Computer Science 2022-12-06 Xiaoxiao Zhao , Jinlong Lei , Li Li , Jie Chen

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

Diffusion models excel in generative tasks, but aligning them with specific objectives while maintaining their versatility remains challenging. Existing fine-tuning methods often suffer from reward over-optimization, while approximate…

Machine Learning · Computer Science 2025-04-18 Sunwoo Kim , Minkyu Kim , Dongmin Park

The recent, impressive advances in algorithmic generation of high-fidelity image, audio, and video are largely due to great successes in score-based diffusion models. A key implementing step is score matching, that is, the estimation of the…

Machine Learning · Statistics 2024-09-12 Zehao Dou , Subhodh Kotekal , Zhehao Xu , Harrison H. Zhou

Diffusion models are a class of flexible generative models trained with an approximation to the log-likelihood objective. However, most use cases of diffusion models are not concerned with likelihoods, but instead with downstream objectives…

Machine Learning · Computer Science 2024-01-08 Kevin Black , Michael Janner , Yilun Du , Ilya Kostrikov , Sergey Levine

The diffusion model has shown remarkable performance in modeling data distributions and synthesizing data. However, the vanilla diffusion model requires complete or fully observed data for training. Incomplete data is a common issue in…

Machine Learning · Computer Science 2023-07-04 Yidong Ouyang , Liyan Xie , Chongxuan Li , Guang Cheng

The probabilistic diffusion model has become highly effective across various domains. Typically, sampling from a diffusion model involves using a denoising distribution characterized by a Gaussian with a learned mean and either fixed or…

Machine Learning · Computer Science 2025-02-20 Zijing Ou , Mingtian Zhang , Andi Zhang , Tim Z. Xiao , Yingzhen Li , David Barber

Diffusion models excel at generative modeling (e.g., text-to-image) but sampling requires multiple denoising network passes, limiting practicality. Efforts such as progressive distillation or consistency distillation have shown promise by…

Machine Learning · Computer Science 2025-04-01 Risheek Garrepalli , Shweta Mahajan , Munawar Hayat , Fatih Porikli

A non-parametric extension of control variates is presented. These leverage gradient information on the sampling density to achieve substantial variance reduction. It is not required that the sampling density be normalised. The novel…

Methodology · Statistics 2016-04-05 Chris J. Oates , Mark Girolami , Nicolas Chopin

Many reinforcement learning approaches rely on temporal-difference (TD) learning to learn a critic. However, TD-learning updates can be high variance. Here, we introduce a model-based RL framework, Taylor TD, which reduces this variance in…

Machine Learning · Computer Science 2023-10-19 Michele Garibbo , Maxime Robeyns , Laurence Aitchison

This paper investigates score-based diffusion models when the underlying target distribution is concentrated on or near low-dimensional manifolds within the higher-dimensional space in which they formally reside, a common characteristic of…

Machine Learning · Computer Science 2025-01-03 Gen Li , Yuling Yan

Adapting a pretrained diffusion model to new objectives at inference time remains an open problem in generative modeling. Existing steering methods suffer from inaccurate value estimation, especially at high noise levels, which biases…

Machine Learning · Computer Science 2025-06-27 Vineet Jain , Kusha Sareen , Mohammad Pedramfar , Siamak Ravanbakhsh