AI Paper Atlas

Research map / Time series / Foundation models for time series

Zero-shot Forecasting by Simulation Alone

Boris N. Oreshkin, Mayank Jauhari, Ravi Kiran Selvam, Malcolm Wolff, Wenhao Pan, Shankar Ramasubramanian, Kin G. Olivares, Tatiana Konstantinova, Andres Potapczynski, Mengfei Cao, Dmitry Efimov, Michael W. Mahoney and 1 more

ICLR 2026 · Time series › Foundation models for time series · approach: Time series foundation models · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SARIMA-2 multi-seasonality superposition (ablation)PatchTST-SarSim0 (250K steps) · GiftEvalsCRPS: 0.647 -> 0.576Improved
add SARIMA-2 multi-seasonality superposition (ablation)NBEATS-SarSim0 · GiftEvalsCRPS: 0.655 -> 0.602Improved
add SARIMA-2 multi-seasonality superposition (ablation)NBEATS-SarSim0 · M-SeriesMASE: 0.941 -> 0.869Improved
add heavy-tailed Noisers (ablation)PatchTST-SarSim0 (250K steps) · GiftEvalsCRPS: 0.594 -> 0.576Improved
add heavy-tailed Noisers (ablation)PatchTST-SarSim0 (250K steps) · M-SeriesMASE: 0.861 -> 0.922Hurt
add heavy-tailed Noisers (ablation)NBEATS-SarSim0 · GiftEvalsCRPS: 0.609 -> 0.602No clear effect
add heavy-tailed Noisers (ablation)NBEATS-SarSim0 · M-SeriesMASE: 0.860 -> 0.869No clear effect
train 500K instead of 250K steps (ablation)PatchTST-SarSim0 · M-SeriesMASE: 0.922 -> 0.877Improved
train 500K instead of 250K steps (ablation)PatchTST-SarSim0 · GiftEvalsCRPS: 0.576 -> 0.573No clear effect
pretrain on SarSim0 instead of KernelSynth dataPatchTST · GiftEvalsCRPS: 0.702 -> 0.573Improved
pretrain on SarSim0 instead of ForecastPFN dataPatchTST · GiftEvalsCRPS: 1.060 -> 0.573Improved
pretrain on SarSim0 instead of KernelSynth dataNBEATS · M-SeriesMASE: 1.033 -> 0.869Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy