OMLT: Optimization & Machine Learning Toolkit

Authors: Francesco Ceccon, Jordan Jalving, Joshua Haddad, Alexander Thebelt, Calvin Tsay, Carl D Laird, Ruth Misener

JMLR 2022 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate how to use OMLT for solving decision-making problems in both computer science and engineering. Our mnist example {dense, cnn}.ipynb notebooks verify dense and convolutional NNs on MNIST (Le Cun et al., 2010).
Researcher Affiliation Academia 1 Department of Computing, Imperial College London, 180 Queen s Gate, SW7 2AZ, UK 2 Center for Computing Research, Sandia National Laboratories, Albuquerque, NM 87123, USA 3 Department of Chemical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Pseudocode No The paper describes the design and functionality of the OMLT toolkit and its integration with Pyomo. It does not include any structured pseudocode or algorithm blocks.
Open Source Code Yes The optimization and machine learning toolkit (https://github.com/cog-imperial/OMLT, OMLT 1.0) is an open-source software package enabling optimization over high-level representations of neural networks (NNs) and gradient-boosted trees (GBTs).
Open Datasets Yes Our mnist example {dense, cnn}.ipynb notebooks verify dense and convolutional NNs on MNIST (Le Cun et al., 2010).
Dataset Splits No The paper mentions using MNIST for verification examples but does not provide specific details on dataset splits (e.g., percentages for training, validation, or test sets).
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory, or processing power) used for running experiments.
Software Dependencies No The paper mentions several software dependencies like Pyomo, ONNX, Keras, PyTorch, and TensorFlow, but does not provide specific version numbers for these components.
Experiment Setup No The paper describes the OMLT framework and different optimization formulations for neural networks and gradient-boosted trees. However, it does not provide specific experimental setup details such as hyperparameters (e.g., learning rates, batch sizes, epochs) or training configurations.