Linear Time Computation of Moments in Sum-Product Networks

Authors: Han Zhao, Geoffrey J. Gordon

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate the usefulness of our linear time algorithm by applying it to develop a linear time assume density filter (ADF) for SPNs. Using Alg. 1 as a sub-routine, both ADF and BMM enjoy linear running time, sharing the same order of time complexity as CCCP. However, since CCCP directly optimizes over the data log-likelihood, in practice we observe that CCCP often outperforms ADF and BMM in log-likelihood scores.
Researcher Affiliation Academia Han Zhao Machine Learning Department Carnegie Mellon University Pittsburgh, PA 15213 han.zhao@cs.cmu.edu Geoff Gordon Machine Learning Department Carnegie Mellon University Pittsburgh, PA 15213 ggordon@cs.cmu.edu
Pseudocode Yes Algorithm 1 Linear Time Exact Moment Computation Algorithm 2 Assumed Density Filtering for SPN
Open Source Code No The paper does not provide any explicit statements or links indicating the release of open-source code for the described methodology.
Open Datasets No The paper describes applying the algorithm to 'develop a linear time assume density filter (ADF) for SPNs' and 'learn the parameters of SPNs in an online fashion'. However, it does not specify any particular dataset used for this application, nor does it provide concrete access information (link, DOI, formal citation) to any public dataset.
Dataset Splits No The paper discusses algorithmic efficiency and application to online learning but does not provide specific details on dataset splits (e.g., percentages or sample counts) for training, validation, or testing.
Hardware Specification No The paper does not specify any hardware details (e.g., GPU/CPU models, memory) used for running experiments or for the practical observations mentioned.
Software Dependencies No The paper does not list specific software components with their version numbers required to replicate the work.
Experiment Setup No The paper describes algorithms and their properties but does not provide specific experimental setup details such as hyperparameter values, training configurations, or system-level settings.