Min-Max Propagation

Authors: Christopher Srinivasa, Inmar Givoni, Siamak Ravanbakhsh, Brendan J. Frey

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

Reproducibility Variable Result LLM Response
Research Type Experimental 5 Experiments and Applications In the first part of this section we compare min-max propagation with the only alternative min-max inference method over FGs that relies on sum-product reduction. In the second part, we formulate the real-world problem of makespan minimization as a min-max inference problem, with high-order factors. ... For N = 10 we also report the exact min-max solutions. ... Results. Fig. 4 compares the performance of sum-product reduction that relies on PBP with min-max propagation and brute-force. For min-max propagation we report the results for three different decimation procedures.
Researcher Affiliation Collaboration Christopher Srinivasa University of Toronto Borealis AI Inmar Givoni University of Toronto Siamak Ravanbakhsh University of British Columbia Brendan J. Frey University of Toronto Vector Institute Deep Genomics
Pseudocode No No structured pseudocode or algorithm blocks are present. Section 4 describes a
Open Source Code No The paper does not contain any statement about making the source code available, nor does it provide a link to a code repository.
Open Datasets No The paper refers to
Dataset Splits No The paper does not specify exact training, validation, or test dataset splits (percentages or counts), nor does it describe a cross-validation setup or reference predefined splits with specific citations or access details for partitioning the data.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, processors, memory, or cloud computing instance types) used for running the experiments are mentioned in the paper.
Software Dependencies No The paper mentions 'Perturbed Belief Propagation (PBP)' and 'IBM s CPLEX solver' but does not provide specific version numbers for these or any other software dependencies.
Experiment Setup Yes Min-max propagation is run for a maximum T = 1000 iterations or until convergence, whichever comes first. ... The PBP used in the sum-product reduction requires a fixed T; we report the results for T equal to the worse case min-max convergence iterations (see appendix) and T = 1000 iterations.