Pith. sign in

REVIEW 6 cited by

Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2101.12072 v2 pith:U2EV6LX3 submitted 2021-01-28 cs.LG cs.AI

Kashif Rasul , Calvin Seward , Ingmar Schuster , Roland Vollgraf This is my paper
classification cs.LGcs.AI
keywords probabilistictimeautoregressivedatadiffusionforecastingmodelmodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this work, we propose \texttt{TimeGrad}, an autoregressive model for multivariate probabilistic time series forecasting which samples from the data distribution at each time step by estimating its gradient. To this end, we use diffusion probabilistic models, a class of latent variable models closely connected to score matching and energy-based methods. Our model learns gradients by optimizing a variational bound on the data likelihood and at inference time converts white noise into a sample of the distribution of interest through a Markov chain using Langevin sampling. We demonstrate experimentally that the proposed autoregressive denoising diffusion model is the new state-of-the-art multivariate probabilistic forecasting method on real-world data sets with thousands of correlated dimensions. We hope that this method is a useful tool for practitioners and lays the foundation for future research in this area.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. StrideDiffusion: Accelerating Diffusion Models for Time-series Generation

    cs.AI 2026-07 conditional novelty 6.0 of 10

    A training-free sampler that adapts diffusion denoising strides to spectral band activity, cutting inference steps from 500-1000 to 14-66 with mostly comparable quality.

  2. TimePre: Bridging Accuracy, Efficiency, and Stability in Probabilistic Time-Series Forecasting

    cs.LG 2025-11 unverdicted novelty 5.0 of 10

    TimePre unifies MLP speed and MCL distributional power via Stabilized Instance Normalization to deliver SOTA probabilistic accuracy, orders-of-magnitude faster inference, and improved stability over prior MCL methods.

  3. CSI Prediction Using Diffusion Models

    eess.SP 2025-10 conditional novelty 5.0 of 10

    Diffusion-based CSI predictors conditioned on temporal encoders report NMSE gains of 5–8 dB over GRU, ConvLSTM, and LinFormer baselines in 3GPP CDL simulations.

  4. Conditional Deep Levy Models for Exotic Derivatives: History-Aware Path Generation and P-Q Payoff Diagnostics

    q-fin.PR 2025-09 reject novelty 5.0 of 10

    The abstract presents a history-aware diffusion path generator and P-Q payoff diagnostic with reported CRPS improvements, but the body does not contain the corresponding method or results.

  5. MR-ImagenTime: Multi-Resolution Time Series Generation through Dual Image Representations

    cs.LG 2026-03 unverdicted novelty 4.0 of 10

    MR-CDM uses hierarchical multi-resolution decomposition and multi-scale conditional diffusion to generate forecasts that reduce MAE and RMSE by 6-10% versus baselines like CSDI and Informer on four datasets.

  6. A Review of Diffusion-based Simulation-Based Inference: Foundations and Applications in Non-Ideal Data Scenarios

    cs.LG 2025-12 accept novelty 2.0 of 10

    A synthesis of diffusion-based simulation-based inference methods that address model misspecification, irregular observations, and missing data in scientific applications.

Pith tools