Unconditional flow-based time series generation with equivariance-regularised latent spaces

• URL: http://arxiv.org/abs/2601.22848v1
• Date: Fri, 30 Jan 2026 11:19:33 GMT
• Title: Unconditional flow-based time series generation with equivariance-regularised latent spaces
• Authors: Camilo Carvajal Reyes, Felipe Tobar,
• Abstract summary: Flow-based models have proven successful for time-series generation.<n>However, how to design latent representations with desirable equivariance properties for time-series generative modelling remains underexplored.<n>We propose a latent flow-matching framework in which equivariance is explicitly encouraged through a simple regularisation of a pre-trained autoencoder.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Flow-based models have proven successful for time-series generation, particularly when defined in lower-dimensional latent spaces that enable efficient sampling. However, how to design latent representations with desirable equivariance properties for time-series generative modelling remains underexplored. In this work, we propose a latent flow-matching framework in which equivariance is explicitly encouraged through a simple regularisation of a pre-trained autoencoder. Specifically, we introduce an equivariance loss that enforces consistency between transformed signals and their reconstructions, and use it to fine-tune latent spaces with respect to basic time-series transformations such as translation and amplitude scaling. We show that these equivariance-regularised latent spaces improve generation quality while preserving the computational advantages of latent flow models. Experiments on multiple real-world datasets demonstrate that our approach consistently outperforms existing diffusion-based baselines in standard time-series generation metrics, while achieving orders-of-magnitude faster sampling. These results highlight the practical benefits of incorporating geometric inductive biases into latent generative models for time series.

Related papers

• Approximate equivariance via projection-based regularisation [1.5755923640031846]
  Non-equivariant models have regained attention, due to their better runtime performance and imperfect symmetries.<n>This has motivated the development of approximately equivariant models that strike a middle ground between respecting symmetries and fitting the data distribution.<n>We present a mathematical framework for computing the non-equivariance penalty exactly and efficiently in both the spatial and spectral domain.
  arXiv  Detail & Related papers  (2026-01-08T15:35:42Z)
• TimeFlow: Towards Stochastic-Aware and Efficient Time Series Generation via Flow Matching Modeling [2.74279932215302]
  Time series data has emerged as a critical research topic due to its broad utility in supporting downstream time series mining tasks.<n>We propose TimeFlow, a novel flow matching framework that integrates a encoder-only architecture.<n>Our model consistently outperforms strong baselines in generation quality, diversity, and efficiency.
  arXiv  Detail & Related papers  (2025-11-11T08:28:26Z)
• Wavelet-based Disentangled Adaptive Normalization for Non-stationary Times Series Forecasting [23.34966767653385]
  We propose Wavelet-based Disentangled Adaptive Normalization (WDAN) to address non-stationarity in time series forecasting.<n>WDAN uses discrete wavelet transforms to break down the input into low-frequency trends and high-frequency fluctuations.<n>Experiments on multiple benchmarks demonstrate that WDAN consistently improves forecasting accuracy across various backbone model.
  arXiv  Detail & Related papers  (2025-06-06T08:25:29Z)
• Solving Inverse Problems with FLAIR [68.87167940623318]
  We present FLAIR, a training-free variational framework that leverages flow-based generative models as prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• Timer-XL: Long-Context Transformers for Unified Time Series Forecasting [67.83502953961505]
  We present Timer-XL, a causal Transformer for unified time series forecasting.<n>Based on large-scale pre-training, Timer-XL achieves state-of-the-art zero-shot performance.
  arXiv  Detail & Related papers  (2024-10-07T07:27:39Z)
• TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model [11.281386703572842]
  TimeDiT is a diffusion transformer model that combines temporal dependency learning with probabilistic sampling.<n>TimeDiT employs a unified masking mechanism to harmonize the training and inference process across diverse tasks.<n>Our systematic evaluation demonstrates TimeDiT's effectiveness both in fundamental tasks, i.e., forecasting and imputation, through zero-shot/fine-tuning.
  arXiv  Detail & Related papers  (2024-09-03T22:31:57Z)
• On the Trajectory Regularity of ODE-based Diffusion Sampling [79.17334230868693]
  Diffusion-based generative models use differential equations to establish a smooth connection between a complex data distribution and a tractable prior distribution. In this paper, we identify several intriguing trajectory properties in the ODE-based sampling process of diffusion models.
  arXiv  Detail & Related papers  (2024-05-18T15:59:41Z)
• Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Time [49.598085130313514]
  We propose discrete non-Markov diffusion models (DNDM), which naturally induce the predetermined transition time set.<n>This enables a training-free sampling algorithm that significantly reduces the number of function evaluations.<n>We study the transition from finite to infinite step sampling, offering new insights into bridging the gap between discrete and continuous-time processes.
  arXiv  Detail & Related papers  (2023-12-14T18:14:11Z)
• Time-series Generation by Contrastive Imitation [87.51882102248395]
  We study a generative framework that seeks to combine the strengths of both: Motivated by a moment-matching objective to mitigate compounding error, we optimize a local (but forward-looking) transition policy. At inference, the learned policy serves as the generator for iterative sampling, and the learned energy serves as a trajectory-level measure for evaluating sample quality.
  arXiv  Detail & Related papers  (2023-11-02T16:45:25Z)
• Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement [51.55157852647306]
  Time series forecasting has been a widely explored task of great importance in many applications. It is common that real-world time series data are recorded in a short time period, which results in a big gap between the deep model and the limited and noisy time series. We propose to address the time series forecasting problem with generative modeling and propose a bidirectional variational auto-encoder equipped with diffusion, denoise, and disentanglement.
  arXiv  Detail & Related papers  (2023-01-08T12:20:46Z)
• Score-based Continuous-time Discrete Diffusion Models [102.65769839899315]
  We extend diffusion models to discrete variables by introducing a Markov jump process where the reverse process denoises via a continuous-time Markov chain. We show that an unbiased estimator can be obtained via simple matching the conditional marginal distributions. We demonstrate the effectiveness of the proposed method on a set of synthetic and real-world music and image benchmarks.
  arXiv  Detail & Related papers  (2022-11-30T05:33:29Z)
• TACTiS: Transformer-Attentional Copulas for Time Series [76.71406465526454]
  estimation of time-varying quantities is a fundamental component of decision making in fields such as healthcare and finance. We propose a versatile method that estimates joint distributions using an attention-based decoder. We show that our model produces state-of-the-art predictions on several real-world datasets.
  arXiv  Detail & Related papers  (2022-02-07T21:37:29Z)
• Continuous Latent Process Flows [47.267251969492484]
  Partial observations of continuous time-series dynamics at arbitrary time stamps exist in many disciplines. Fitting this type of data using statistical models with continuous dynamics is not only promising at an intuitive level but also has practical benefits. We tackle these challenges with continuous latent process flows (CLPF), a principled architecture decoding continuous latent processes into continuous observable processes using a time-dependent normalizing flow driven by a differential equation. Our ablation studies demonstrate the effectiveness of our contributions in various inference tasks on irregular time grids.
  arXiv  Detail & Related papers  (2021-06-29T17:16:04Z)
• Conditional Sig-Wasserstein GANs for Time Series Generation [8.593063679921109]
  Generative adversarial networks (GANs) have been extremely successful in generating samples, from seemingly high dimensional probability measures. These methods struggle to capture the temporal dependence of joint probability distributions induced by time-series data. Long time-series data streams hugely increase the dimension of the target space, which may render generative modelling infeasible. We propose a generic conditional Sig-WGAN framework by integrating Wasserstein-GANs with mathematically principled and efficient path feature extraction.
  arXiv  Detail & Related papers  (2020-06-09T17:38:55Z)
• Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows [40.9137348900942]
  We propose a novel type of flow driven by a differential deformation of the Wiener process. As a result, we obtain a rich time series model whose observable process inherits many of the appealing properties of its base process.
  arXiv  Detail & Related papers  (2020-02-24T20:13:43Z)

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.