Accelerating Diffusion Transformers with Gaussian Process Rectified Feature Cache

• URL: http://arxiv.org/abs/2609.05981v1
• Date: Sat, 05 Sep 2026 08:54:54 GMT
• Title: Accelerating Diffusion Transformers with Gaussian Process Rectified Feature Cache
• Abstract summary: Diffusion Transformers have become the dominant paradigm in generative AI, but their high computational costs hinder real-time applications.<n>Prediction-based feature caching is widely used to accelerate diffusion transformers; however, as the number of steps increases, the deviation between its predictions and the reference full-compute trajectory gradually grows.<n>An intuitive idea is to use an online regression model to dynamically correct this deviation, but it faces the issue of label data being unavailable during the acceleration process.<n>This paper presents a statistical observation that the residuals between the features of full computation steps using caching methods and reference full-compute trajectory locally exhibit a
• Score: 17.39547918764814
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion Transformers have become the dominant paradigm in generative AI, but their high computational costs severely hinder real-time applications. Prediction-based feature caching is widely used to accelerate diffusion transformers; however, as the number of steps increases, the deviation between its predictions and the reference full-compute trajectory gradually grows. An intuitive idea is to use an online regression model to dynamically correct this deviation, but it faces the issue of label data being unavailable during the acceleration process. This paper presents a statistical observation that the residuals between the features of full computation steps using caching methods and reference full-compute trajectory locally exhibit a zero-mean Gaussian distribution. By treating the features of full computation steps as noisy observations of reference features, the data acquisition problem is resolved. Based on this observation, a plug-and-play GP-Refiner correction framework is proposed. This method utilizes Gaussian Process Regression for correction and, leveraging the properties of GPR, introduces an uncertainty-adaptive computation strategy that triggers necessary full-computation calibration by monitoring the posterior variance in real time. Experiments demonstrate significant improvements across different models when combined with various state-of-the-art methods. Integrating the proposed framework with TaylorSeer reduces the computational load by 19.3% while improving PSNR by 0.9 dB and reducing LPIPS from 0.46 to 0.29. Code is available in https://github.com/Aredstone/GP-Refiner.

Related papers

• Fast Gaussian Process Approximations for Autocorrelated Data [5.614320553305912]
  This paper is concerned with the problem of how to speed up computation for Gaussian process models trained on autocorrelated data.<n>The proposed approaches can remarkably accelerate computation for Gaussian process regression on autocorrelated data without compromising model prediction performance.
  arXiv  Detail & Related papers  (2025-12-02T16:46:07Z)
• Shortening the Trajectories: Identity-Aware Gaussian Approximation for Efficient 3D Molecular Generation [2.631060597686179]
  Probabilistic Generative Models (GPGMs) generate data by reversing a process that corrupts samples with Gaussian noise.<n>These models have achieved state-of-the-art performance across diverse domains, but their practical deployment remains constrained by the high computational cost.<n>We introduce a theoretically grounded and empirically validated framework that improves generation efficiency without sacrificing training granularity or inference fidelity.
  arXiv  Detail & Related papers  (2025-07-11T21:39:32Z)
• Accelerating Diffusion Transformer via Increment-Calibrated Caching with Channel-Aware Singular Value Decomposition [4.0594792247165]
  Diffusion transformer (DiT) models have achieved remarkable success in image generation.<n>We propose increment-calibrated caching, a training-free method for DiT acceleration.<n>Our method eliminates more than 45% and improves IS by 12 at the cost of less than 0.06 FID increase.
  arXiv  Detail & Related papers  (2025-05-09T06:56:17Z)
• Adaptive Multi-step Refinement Network for Robust Point Cloud Registration [82.64560249066734]
  Point Cloud Registration estimates the relative rigid transformation between two point clouds of the same scene.<n>We propose an adaptive multi-step refinement network that refines the registration quality at each step by leveraging the information from the preceding step.<n>Our method achieves state-of-the-art performance on both the 3DMatch/3DLoMatch and KITTI benchmarks.
  arXiv  Detail & Related papers  (2023-12-05T18:59:41Z)
• Neural Operator Variational Inference based on Regularized Stein Discrepancy for Deep Gaussian Processes [22.256068524699472]
  We introduce Neural Operator Variational Inference (NOVI) for Deep Gaussian Processes.<n>NOVI uses a neural generator to obtain a sampler and minimizes the Regularized Stein Discrepancy in L2 space between the generated distribution and true posterior.<n>We demonstrate that the bias introduced by our method can be controlled by multiplying the divergence with a constant, which leads to robust error control and ensures the stability and precision of the algorithm.
  arXiv  Detail & Related papers  (2023-09-22T06:56:35Z)
• Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent [43.097493761380186]
  gradient algorithms are an efficient method of approximately solving linear systems. We show that gradient descent produces accurate predictions, even in cases where it does not converge quickly to the optimum. Experimentally, gradient descent achieves state-of-the-art performance on sufficiently large-scale or ill-conditioned regression tasks.
  arXiv  Detail & Related papers  (2023-06-20T15:07:37Z)
• Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model [89.8764435351222]
  We propose a new family of unbiased estimators called WTA-CRS, for matrix production with reduced variance. Our work provides both theoretical and experimental evidence that, in the context of tuning transformers, our proposed estimators exhibit lower variance compared to existing ones.
  arXiv  Detail & Related papers  (2023-05-24T15:52:08Z)
• Gaussian Process Inference Using Mini-batch Stochastic Gradient Descent: Convergence Guarantees and Empirical Benefits [21.353189917487512]
  gradient descent (SGD) and its variants have established themselves as the go-to algorithms for machine learning problems. We take a step forward by proving minibatch SGD converges to a critical point of the full log-likelihood loss function. Our theoretical guarantees hold provided that the kernel functions exhibit exponential or eigendecay.
  arXiv  Detail & Related papers  (2021-11-19T22:28:47Z)
• Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition [54.07797071198249]
  We introduce a new scalable variational Gaussian process approximation which provides a high fidelity approximation while retaining general applicability. We demonstrate that, on a range of regression and classification problems, our approach can exploit input space symmetries such as translations and reflections. Notably, our approach achieves state-of-the-art results on CIFAR-10 among pure GP models.
  arXiv  Detail & Related papers  (2021-06-10T18:17:57Z)
• Real-Time Regression with Dividing Local Gaussian Processes [62.01822866877782]
  Local Gaussian processes are a novel, computationally efficient modeling approach based on Gaussian process regression. Due to an iterative, data-driven division of the input space, they achieve a sublinear computational complexity in the total number of training points in practice. A numerical evaluation on real-world data sets shows their advantages over other state-of-the-art methods in terms of accuracy as well as prediction and update speed.
  arXiv  Detail & Related papers  (2020-06-16T18:43:31Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)
• SLEIPNIR: Deterministic and Provably Accurate Feature Expansion for Gaussian Process Regression with Derivatives [86.01677297601624]
  We propose a novel approach for scaling GP regression with derivatives based on quadrature Fourier features. We prove deterministic, non-asymptotic and exponentially fast decaying error bounds which apply for both the approximated kernel as well as the approximated posterior.
  arXiv  Detail & Related papers  (2020-03-05T14:33:20Z)
• Improving Sampling Accuracy of Stochastic Gradient MCMC Methods via Non-uniform Subsampling of Gradients [54.90670513852325]
  We propose a non-uniform subsampling scheme to improve the sampling accuracy. EWSG is designed so that a non-uniform gradient-MCMC method mimics the statistical behavior of a batch-gradient-MCMC method. In our practical implementation of EWSG, the non-uniform subsampling is performed efficiently via a Metropolis-Hastings chain on the data index.
  arXiv  Detail & Related papers  (2020-02-20T18:56:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.