Distributionally Robust Graphical Models
Authors: Rizal Fathony, Ashkan Rezaei, Mohammad Ali Bashiri, Xinhua Zhang, Brian Ziebart
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We present exact learning and prediction algorithms for AGM with time complexity similar to existing graphical models and show the practical benefits of our approach with experiments. ... To evaluate our approach, we apply AGM to two different tasks: predicting emotion intensity from a sequence of images, and labeling entities in parse trees with semantic roles. We show the benefit of our method compared with a conditional random field (CRF) and a structured SVM (SSVM). |
| Researcher Affiliation | Academia | Rizal Fathony, Ashkan Rezaei, Mohammad Ali Bashiri, Xinhua Zhang, Brian D. Ziebart Department of Computer Science, University of Illinois at Chicago Chicago, IL 60607 {rfatho2, arezae4, mbashi4, zhangx, bziebart}@uic.edu |
| Pseudocode | No | The paper describes its algorithms in prose but does not provide structured pseudocode blocks or sections formally labeled 'Algorithm'. |
| Open Source Code | No | The paper does not contain any explicit statements about releasing source code for the described methodology or provide a link to a code repository. |
| Open Datasets | Yes | We evaluate our approach in the facial emotion intensity prediction task [46]. ... We evaluate the performance of our algorithm on the semantic role labeling task for the CoNLL 2005 dataset [47]. |
| Dataset Splits | Yes | From the whole 167 sequences, we construct 20 different random splits of the training and the testing datasets with 120 sequences of training samples and 47 sequences of testing samples. We use the training set in the first split to perform cross validation to obtain the best regularization parameters and then use the best parameter in the evaluation phase for all 20 different splits of the dataset. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., library names with versions) needed to replicate the experiment. |
| Experiment Setup | No | The paper mentions performing cross-validation to obtain the best regularization parameters but does not provide the specific values for these parameters or other detailed training configurations such as learning rates, batch sizes, or optimizer settings. |