QDiffusion-TS is the first quantum generative diffusion model for time series, achieving ~44% lower Wasserstein distance on Apple and Amazon stock data and up to 71% better forecasting RMSE with ~1000x fewer parameters than classical diffusion.
hub
arXiv preprint arXiv:2403.01742 , year=
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
Introduces the task of counterfactual time series forecasting with textual conditions plus a text-attribution mechanism that improves accuracy by distinguishing mutable from immutable factors.
Flow matching on time series targets a closed-form nonparametric velocity field that is a similarity-weighted mixture of observed transition velocities, making neural models approximations to an ideal memory-augmented dynamical system sampler.
SRT decomposes low-resolution time series into trend and seasonal components, aligns them via implicit neural representations, and uses cross-resolution attention within a disentangled rectified flow to generate high-resolution outputs, with a scaled SRT-large variant for zero-shot use.
PrismFlow augments flow matching with residual dynamical experts and a winner-take-all objective to reduce spectral distortion and improve mode coverage in time-series generation.
TGSD combines a Hierarchical Spatial Prior Encoder with conditional state-space diffusion to achieve EEG spatial super-resolution, outperforming baselines on reconstruction fidelity and classification on SEED and PhysioNet datasets.
SDFlow learns a global transport map via similarity-driven flow matching in VQ latent space, using low-rank manifold decomposition and a categorical posterior to handle discreteness, yielding SOTA long-horizon performance and inference speedups.
NsDiff combines a denoising diffusion conditional generative model with a pre-trained mean/variance estimator and an uncertainty-aware noise schedule based on the Location-Scale Noise Model to capture time-varying uncertainty in probabilistic forecasting.
MOSAIC structures LLM-based model selection via memory-grounded blueprints and failure-aware RL, reporting gains in performance and traceability on financial time-series tasks over AutoML and agent baselines.
Hybrid CoMeTS-GAN plus diffusion model generates multivariate financial time series claimed to better reproduce stylized facts and inter-asset correlations than prior generative methods.
Hyperparameter-optimized generative models augment scarce flight diversion records and substantially improve prediction accuracy over real data alone.
A temporal extension of TabDDPM generates coherent synthetic time-series sequences on the WISDM dataset that match real distributions and support downstream classification with macro F1 of 0.64.
MSDformer introduces a multi-scale discrete transformer that tokenizes time series at multiple scales and models them autoregressively in discrete space, claiming superior performance over prior DTM methods with rate-distortion theoretical support.
PPM injects parametric structural priors into generative models via a learnable mapping to improve probabilistic forecasts on non-stationary MTS data.