Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Adversarial Constraint Learning for Structured Prediction
Authors: Hongyu Ren, Russell Stewart, Jiaming Song, Volodymyr Kuleshov, Stefano Ermon
IJCAI 2018 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate the proposed framework on three structured prediction problems. First, we aim to track the angle of a pendulum in a video without labels using supervision provided by a physics-based simulator. Next, we extend the output space to higher dimensions and perform human pose estimation in a semi-supervised setting. Lastly, we evaluate our approach on multivariate time series prediction, where the goal is to predict future temperature and humidity. A label simulator is provided for each experiment in place of hand-written constraints. |
| Researcher Affiliation | Academia | Hongyu Ren, Russell Stewart, Jiaming Song, Volodymyr Kuleshov, Stefano Ermon Department of Computer Science, Stanford University EMAIL |
| Pseudocode | No | The paper does not contain any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to open-source code for the described methodology. |
| Open Datasets | Yes | We aim to predict the angle of the pendulum from images in a You Tube video [1]. |
| Dataset Splits | No | The paper specifies training and testing splits for its datasets (e.g., 'We hold out 34 images for evaluation' for pendulum, 'dividing data into training and testing sets of 28 groups and 7 groups' for pose estimation, 'hold out 8 consecutive days for testing and leave the rest for training' for time series), but does not explicitly mention or detail a separate validation set split for hyperparameter tuning. |
| Hardware Specification | No | The paper does not provide specific details regarding the hardware used to run its experiments. |
| Software Dependencies | No | The paper mentions using neural network architectures (CNN, LSTM) and refers to a training procedure from a cited paper, but does not list specific software dependencies with version numbers. |
| Experiment Setup | Yes | We implement rĪø as a 5 layer convolutional neural network with Re LU nonlinearities, and DĻ as a 5-cell LSTM. We use Ī± = 10 in Eq. 5, and the same training procedure and hyperparameters as [Gulrajani et al., 2017] across our experiments. |