Wavelet Fourier Diffuser: Frequency-Aware Diffusion Model for Reinforcement Learning

• URL: http://arxiv.org/abs/2509.19305v1
• Date: Thu, 04 Sep 2025 08:50:31 GMT
• Title: Wavelet Fourier Diffuser: Frequency-Aware Diffusion Model for Reinforcement Learning
• Authors: Yifu Luo, Yongzhe Chang, Xueqian Wang,
• Abstract summary: We propose a novel diffusion-based RL framework that integrates Discrete Wavelet Transform to decompose trajectories into low- and high-frequency components.<n>WFDiffuser effectively mitigates frequency shift, leading to smoother, more stable trajectories and improved decision-making performance.
• Score: 10.270002679268485
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion probability models have shown significant promise in offline reinforcement learning by directly modeling trajectory sequences. However, existing approaches primarily focus on time-domain features while overlooking frequency-domain features, leading to frequency shift and degraded performance according to our observation. In this paper, we investigate the RL problem from a new perspective of the frequency domain. We first observe that time-domain-only approaches inadvertently introduce shifts in the low-frequency components of the frequency domain, which results in trajectory instability and degraded performance. To address this issue, we propose Wavelet Fourier Diffuser (WFDiffuser), a novel diffusion-based RL framework that integrates Discrete Wavelet Transform to decompose trajectories into low- and high-frequency components. To further enhance diffusion modeling for each component, WFDiffuser employs Short-Time Fourier Transform and cross attention mechanisms to extract frequency-domain features and facilitate cross-frequency interaction. Extensive experiment results on the D4RL benchmark demonstrate that WFDiffuser effectively mitigates frequency shift, leading to smoother, more stable trajectories and improved decision-making performance over existing methods.

Related papers

• A Decomposable Forward Process in Diffusion Models for Time-Series Forecasting [2.24303609250571]
  We introduce a model-agnostic forward diffusion process for time-series forecasting that decomposes signals into spectral components.<n>By staging noise injection according to component energy, it maintains high signal-to-noise ratios for dominant frequencies.<n>We show that applying spectral decomposition strategies, such as the Fourier or Wavelet transform, consistently improves upon diffusion models.
  arXiv  Detail & Related papers  (2026-01-29T14:55:43Z)
• Frequency-Constrained Learning for Long-Term Forecasting [15.31488551912888]
  Real-world time series exhibit strong periodic structures arising from physical laws, human routines, or seasonal cycles.<n>Modern deep forecasting models often fail to capture these recurring patterns due to spectral bias and a lack of frequency-aware inductive priors.<n>We propose a simple yet effective method that enhances long-term forecasting by explicitly modeling periodicity.
  arXiv  Detail & Related papers  (2025-08-02T22:12:15Z)
• LSCD: Lomb-Scargle Conditioned Diffusion for Time series Imputation [55.800319453296886]
  Time series with missing or irregularly sampled data are a persistent challenge in machine learning.<n>We introduce a different Lombiable--Scargle layer that enables a reliable computation of the power spectrum of irregularly sampled data.
  arXiv  Detail & Related papers  (2025-06-20T14:48:42Z)
• Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition [83.40450475728792]
  We present Freqformer, a Transformer-based framework specifically designed for image demoir'eing through targeted frequency separation.<n>Our method performs an effective frequency decomposition that explicitly splits moir'e patterns into high-frequency spatially-localized textures and low-frequency scale-robust color distortions.<n>Experiments on various demoir'eing benchmarks demonstrate that Freqformer achieves state-of-the-art performance with a compact model size.
  arXiv  Detail & Related papers  (2025-05-25T12:23:10Z)
• A Fourier Space Perspective on Diffusion Models [6.834230686279937]
  Diffusion models are state-of-the-art generative models on data modalities such as images, audio, proteins and materials.<n>We study the inductive bias of the forward process of diffusion models in Fourier space.
  arXiv  Detail & Related papers  (2025-05-16T14:13:02Z)
• Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learning [81.98675881423131]
  This research addresses the challenge of developing a universal deepfake detector that can effectively identify unseen deepfake images. Existing frequency-based paradigms have relied on frequency-level artifacts introduced during the up-sampling in GAN pipelines to detect forgeries. We introduce a novel frequency-aware approach called FreqNet, centered around frequency domain learning, specifically designed to enhance the generalizability of deepfake detectors.
  arXiv  Detail & Related papers  (2024-03-12T01:28:00Z)
• Time Series Diffusion in the Frequency Domain [54.60573052311487]
  We analyze whether representing time series in the frequency domain is a useful inductive bias for score-based diffusion models. We show that a dual diffusion process occurs in the frequency domain with an important nuance. We show how to adapt the denoising score matching approach to implement diffusion models in the frequency domain.
  arXiv  Detail & Related papers  (2024-02-08T18:59:05Z)
• Incremental Spatial and Spectral Learning of Neural Operators for Solving Large-Scale PDEs [86.35471039808023]
  We introduce the Incremental Fourier Neural Operator (iFNO), which progressively increases the number of frequency modes used by the model. We show that iFNO reduces total training time while maintaining or improving generalization performance across various datasets. Our method demonstrates a 10% lower testing error, using 20% fewer frequency modes compared to the existing Fourier Neural Operator, while also achieving a 30% faster training.
  arXiv  Detail & Related papers  (2022-11-28T09:57:15Z)
• Transform Once: Efficient Operator Learning in Frequency Domain [69.74509540521397]
  We study deep neural networks designed to harness the structure in frequency domain for efficient learning of long-range correlations in space or time. This work introduces a blueprint for frequency domain learning through a single transform: transform once (T1)
  arXiv  Detail & Related papers  (2022-11-26T01:56:05Z)
• Fast Sampling of Diffusion Models via Operator Learning [74.37531458470086]
  We use neural operators, an efficient method to solve the probability flow differential equations, to accelerate the sampling process of diffusion models. Compared to other fast sampling methods that have a sequential nature, we are the first to propose a parallel decoding method. We show our method achieves state-of-the-art FID of 3.78 for CIFAR-10 and 7.83 for ImageNet-64 in the one-model-evaluation setting.
  arXiv  Detail & Related papers  (2022-11-24T07:30:27Z)
• A Time-domain Generalized Wiener Filter for Multi-channel Speech Separation [11.970226369922598]
  Frequency-domain neural beamformers are the mainstream methods for recent multi-channel speech separation models. We propose a time-domain Wiener generalized filter (TD-GWF) as an extension to the conventional frequency-domain beamformers. Experiment results show that a significant performance improvement can be achieved by replacing frequency-domain beamformers by the TD-GWF.
  arXiv  Detail & Related papers  (2021-12-07T07:16:43Z)

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.