arXiv (All)
open access
One Patch, Three Roles: What Is Actually Coupled in Autoregressive Time-Series Forecasting?
Patch-based autoregressive time-series forecasting often ties input representation, learned transitions, and recursive execution to one patch length. We ask which of these roles can be adjusted separately. A supporting atomic-encoding study finds greater sensitivity to model width than to atom group
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- ChronoSSM: Training for Temporally Aware Representations in Autoregressive State Space Models#444599
- HALO: Enhancing Time Series Generation via Hyperspherical Latents and Masked AutoregRessive Modeling#1131662
- QUALS: Corpus Equilibrium for Universal Forecasting via Pattern Quantization and Learnability Synchronization#1048806
- Learning to Difference: Adaptive Reversible Differencing (AdaRDiff) for Time Series Forecasting#618590
- APEBench: A Benchmark for Autoregressive Neural Emulators of PDEs#684187
Record · ID 1049422
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive