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].

Learning and Inference in Hilbert Space with Quantum Graphical Models

Authors: Siddarth Srinivasan, Carlton Downey, Byron Boots

NeurIPS 2018 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We present experimental results showing that HSE-HQMMs are competitive with state-of-the-art models like LSTMs and PSRNNs on several datasets, while also providing a nonparametric method for maintaining a probability distribution over continuous-valued features. 6 Experiments We use the following datasets in our experiments:
Researcher Affiliation Academia Siddarth Srinivasan College of Computing Georgia Tech Atlanta, GA 30332 EMAIL Carlton Downey Department of Machine Learning Carnegie Mellon University Pittsburgh, PA 15213 EMAIL Byron Boots College of Computing Georgia Tech Atlanta, GA 30332 EMAIL
Pseudocode Yes Algorithm 1 Learning Algorithm using Two-Stage Regression for HSE-HQMMs
Open Source Code No Code will be made available at https://github.com/cmdowney/hsehqmm
Open Datasets Yes Penn Tree Bank (PTB) Marcus et al. [1993]. Swimmer Simulated swimmer robot from Open AI gym2. We collect 25 trajectories from a robot... Mocap Human Motion Capture Dataset. We collect 48 skeletal tracks from three human subjects...
Dataset Splits No We train a character-prediction model with a train/test split of 120780/124774 characters due to hardware limitations. We collect 25 trajectories from a robot... with a 20/5 train/test split. We collect 48 skeletal tracks from three human subjects with a 40/8 train/test split. Only train/test splits are specified, not validation.
Hardware Specification No No specific hardware details (like CPU/GPU models, memory, or specific cloud instances) used for the experiments are provided.
Software Dependencies No No specific software dependencies with version numbers are mentioned in the paper.
Experiment Setup No Hyperparameters and other experimental details can be found in Appendix E. No specific hyperparameter values or detailed training configurations are provided in the main body of the paper.