Copula Conformal prediction for multi-step time series prediction
Authors: Sophia Huiwen Sun, Rose Yu
ICLR 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | On four synthetic and real-world multivariate time series datasets, we show that Copula CPTS produces more calibrated and efficient confidence intervals for multi-step prediction tasks than existing techniques. Our code is open-sourced at https://github.com/Rose-STL-Lab/Copula CPTS. |
| Researcher Affiliation | Academia | Sophia Sun University of California, San Diego shs066@ucsd.edu Rose Yu University of California, San Diego roseyu@ucsd.edu |
| Pseudocode | Yes | Algorithm 1: Copula Conformal Time Series Prediction (Copula CPTS) |
| Open Source Code | Yes | Our code is open-sourced at https://github.com/Rose-STL-Lab/Copula CPTS. |
| Open Datasets | Yes | On four synthetic and real-world multivariate time series datasets, we show that Copula CPTS produces more calibrated and efficient confidence intervals for multi-step prediction tasks than existing techniques. Our code is open-sourced at https://github.com/Rose-STL-Lab/Copula CPTS. Particle Sim (Kipf et al., 2018), and drone trajectory following simulated with Python Robotics (Sakai et al., 2018). The COVID-19 dataset is downloaded directly from the official UK government website https://coronavirus.data.gov.uk/details/download by selecting region for area type and new Cases By Publish Date for metric. The Argoverse autonomous vehicle motion forecasting dataset (Chang et al., 2019) is a widely used vehicle trajectory prediction benchmark. |
| Dataset Splits | Yes | We generate 5000 samples for each dataset, and split the data by 45/45/10 for train, calibration, and test, respectively. For the Argoverse data, We split 90/10 into a training set and validation set of size 185,348 and 20,594 respectively. |
| Hardware Specification | Yes | For each run of our experiments, the calibration and prediction steps of Copula CPTS combined took less than 1 minute to run on an Apple M1 CPU. |
| Software Dependencies | No | The paper does not provide specific version numbers for software dependencies (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | Yes | The underlying forecasting model for the particle experiments is an 1-layer LSTM network with embedding size = 24. The hidden state is then passed through a linear network to forecast the timesteps concurrently (output has dimension k dy). We train the model for 150 epochs with batch size 128. For the drone trajectory forecasting task, we use the same LSTM forecasting network as the particle dataset, but with its hidden size increased to 128. We train the model for 500 epochs with batch size 128. The base forecasting model for Covid-19 dataset is the same as the model for synthetic datasets, with hidden size = 128, and were trained for 150 epochs with batch size 128. |