Time series generation with spectrally aligned latent flow matching
Spectrally aligned latent flow matching generates time series that preserve Fourier, wavelet, and signature structure.
Latent flow models compress time series but can distort spectra, limiting their use as training surrogates. The authors train the latent space for flow matching with fine-tuning losses from Fourier, wavelet, and signature transforms so synthetic samples keep relevant dynamics. They compare the aligned generator with a base latent-flow model and prior methods on long-range univariate and multivariate benchmarks. Reported gains cover signal realism and compute cost while matching the local structure of the training data.
- Spectral mismatch is a known artefact of latent time-series generators.
- Fine-tuning uses Fourier, wavelet, and signature-transform losses.
- Models are evaluated on long-range univariate and multivariate benchmarks.
- Authors report better realism and efficiency than a base latent-flow model.
From the original article
1 min read at arxiv.orgLatent flow models have proven to be a reliable and cost-effective method for time series generation. However, the latent compression induces unwanted artefacts, such as a spectral mismatch with respect to the underlying dataset, thus hindering their use as training surrogates.
By Camilo Carvajal Reyes · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.