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 Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Improving Predictive State Representations via Gradient Descent
Authors: Nan Jiang, Alex Kulesza, Satinder Singh
AAAI 2016 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We ο¬rst show on synthetic domains that our proposed gradient procedure can improve the model, and that spectral learning provides a useful initialization. We investigate the effectiveness of our gradient procedure on a character-level language modeling problem using Wikipedia data |
| Researcher Affiliation | Academia | Nan Jiang and Alex Kulesza and Satinder Singh EMAIL, EMAIL, EMAIL Computer Science & Engineering University of Michigan |
| Pseudocode | Yes | Algorithm 1 Stochastic Gradient Descent with Contrastive Divergence for Predictive State Representations. |
| Open Source Code | No | The paper does not contain an explicit statement about releasing their own source code or provide a link to a repository for it. |
| Open Datasets | Yes | We investigate the effectiveness of our gradient procedure on a character-level language modeling problem using Wikipedia data (Sutskever, Martens, and Hinton 2011) |
| Dataset Splits | No | The paper mentions training and testing datasets, but does not explicitly specify a validation dataset split. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers. |
| Experiment Setup | Yes | We use a constant learning rate of Ξ· = 10 6. To prevent the model parameters from experiencing sudden changes due to occasional stochastic gradients with a large magnitude, we rescale the stochastic gradient term Ξ to guarantee that Ξ 10. The learning rate and momentum parameters are set to 10 7 and 0.9, respectively. |