Research map / Time series / Causal and generative time series
AmortizedPeriod: Attention-based Amortized Inference for Periodicity Identification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes AmortizedPeriod, an attention-based amortized inference model for periodicity identification in time series that reuses knowledge from previously observed series to speed up and improve inference on new data.
Problem
Periodicity detection in time series lacks robustness in real-world settings and cannot leverage previously observed time series to accelerate and improve inference on new data.
Approach
Uses an attention-based amortized inference network that learns from prior time series so that periodicity is identified on new data with a memory of earlier observations, rather than running per-series statistical detection from scratch.
Closest papers by meaning
- An Unsupervised Approach for Periodic Source Detection in Time Series (ICML 2024 · similarity 0.88)
- Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysis (NeurIPS 2024 · similarity 0.85)
- Compositional simulation-based inference for time series (ICLR 2025 · similarity 0.85)
- Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach (NeurIPS 2025 · similarity 0.85)
- MPTSNet: Integrating Multiscale Periodic Local Patterns and Global Dependencies for Multivariate Time Series Classification (AAAI 2025 · similarity 0.84)
- Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series (ICLR 2025 · similarity 0.84)
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.